Medium voltage network flexible interconnection method and system

Abstract

The application provides a medium-voltage network frame flexible interconnection method and system, relates to the power distribution network networking technical field, and the method comprises the following steps: a typical working condition scene library is constructed; the installation position and installation capacity of the flexible interconnection equipment are taken as decision variables, and the minimum double-layer flexible interconnection loss is taken as a decision constraint to identify a flexible interconnection scheme; a local sensitive area weight adapter is introduced to generate an adaptive control strategy for the initial flexible interconnection scheme; real-time operation conditions are acquired, matched with the typical working condition scene library, and controlled according to the matching result to match the typical working condition control strategy and complete the flexible interconnection. Through the application, the technical problem that the control of the fixed-structure power distribution network under different operation conditions is not flexible enough due to the complex and changeable power grid operation state in the prior art, thereby affecting the stability of the power distribution network, is solved. The flexible interconnection equipment configuration is flexibly adjusted under different operation states, and the stability of the power distribution network is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network networking, in particular to a medium-voltage network architecture flexible interconnection method and system. BACKGROUND

[0002] The existing power distribution network architecture mostly adopts a traditional radial structure and a low-voltage area chain independent operation mode, which can better meet the power grid load demand in the early stage, but with the access of distributed power sources, some new technical problems have emerged. In particular, the volatility and intermittency characteristics of distributed power sources (such as wind energy and solar energy) have brought great operation pressure to the power distribution network. At present, the power distribution network usually adopts a fixed architecture and operation mode, lacking flexibility in adapting to changes in the operation state of the power grid. The complexity of the operation state of the power grid and the volatility of the distributed power sources make it difficult for the current control strategy to effectively respond, thereby affecting the stability and operation efficiency of the power distribution network.

[0003] In summary, in the prior art, there is a technical problem that the control of the power distribution network with a fixed structure is not flexible under different operation conditions due to the complex and variable operation state of the power grid, thereby affecting the stability of the power distribution network. SUMMARY

[0004] The purpose of the present application is to provide a medium-voltage network architecture flexible interconnection method and system to solve the technical problem in the prior art that the control of the power distribution network with a fixed structure is not flexible under different operation conditions due to the complex and variable operation state of the power grid, thereby affecting the stability of the power distribution network.

[0005] In view of the above problems, the present application provides a medium-voltage network architecture flexible interconnection method and system.

[0006] In a first aspect, the present application provides a medium-voltage network architecture flexible interconnection method, which is realized by a medium-voltage network architecture flexible interconnection system, wherein the medium-voltage network architecture flexible interconnection method comprises: acquiring a historical load data set, a historical energy storage data set and a historical operation data set of a target medium-voltage power distribution network, performing operation typical condition extraction, and constructing an operation typical condition scenario library; taking the installation position and installation capacity of a flexible interconnection device as decision variables, taking the minimum double-layer flexible interconnection loss as a decision constraint, combining the operation typical condition scenario library to perform flexible interconnection scheme identification, and obtaining an initial flexible interconnection scheme; introducing a local sensitive area weight adapter, combining the operation typical condition scenario library to perform adaptive control strategy generation on the initial flexible interconnection scheme, and obtaining an operation typical condition control strategy library; acquiring a real-time operation condition of the target medium-voltage power distribution network, matching the real-time operation condition with the operation typical condition scenario library, and according to the matching result, calling a matching operation typical condition control strategy in the operation typical condition control strategy library for control, and completing flexible interconnection.

[0007] Optionally, the historical load data set, the historical energy storage data set and the historical operation data set are subjected to time sequence alignment and missing value completion processing to construct a comprehensive operation data set; the comprehensive operation data set is subjected to single-peak mode constraint peak value detection to determine a key operation time set; the comprehensive operation data set is topologically divided according to a preset power flow statistical window with the key operation time set as the center to determine an operation topological segment set and an operation topological segment feature set; and the operation topological segment set is clustered according to a preset clustering scale based on the operation topological segment feature set to construct an operation typical working condition scenario library.

[0008] Optionally, local fluctuation maximum value comprehensive operation data set is determined by traversing the comprehensive operation data set to extract local fluctuation maximum values; a single-peak mode interval is formed by expanding to both sides with the local fluctuation maximum value comprehensive operation data set as the center to obtain a local fluctuation maximum value comprehensive operation data interval set; the local fluctuation maximum value comprehensive operation data interval set is screened according to a preset interval width threshold and a preset peak value amplitude threshold to obtain a screened local fluctuation maximum value comprehensive operation data interval set; and the time of the local fluctuation maximum value comprehensive operation data corresponding to the screened local fluctuation maximum value comprehensive operation data interval set is added to the key operation time set.

[0009] Optionally, the comprehensive operation data set is subjected to front and rear data topology extraction according to the preset power flow statistical window in combination with the key operation time set to determine the operation topological segment set; and the topological segment feature set is determined by traversing the operation topological segment set to perform feature recognition.

[0010] Optionally, the operation topological segment feature set is subjected to same-type aggregation according to a preset clustering scale to obtain a plurality of clustered operation topological segment feature sets; the operation topological segment set is subjected to mapping clustering according to the plurality of clustered operation topological segment feature sets to obtain a plurality of mapping clustered operation topological segment sets; the number of segments in the plurality of mapping clustered operation topological segment sets is respectively counted, and the counting results are compared with the total segment number of the plurality of mapping clustered operation topological segment sets to obtain a plurality of probability coefficients; the mean value of the plurality of mapping clustered operation topological segment sets is calculated to obtain a plurality of operation typical working conditions, and the plurality of operation typical working conditions are associated with the plurality of probability coefficients to construct the operation typical working condition scenario library.

[0011] Optionally, the installation position and installation capacity of the flexible interconnection device are taken as decision variables, and flexible interconnection scheme identification is performed based on the running typical working condition scenario library to obtain an independent flexible interconnection scheme set; the minimum double-layer flexible interconnection loss is taken as a decision constraint, and scheme reliability coefficient identification is performed on the independent flexible interconnection scheme set to obtain a scheme reliability coefficient set; the independent flexible interconnection scheme corresponding to the maximum value in the scheme reliability coefficient set is taken as the initial flexible interconnection scheme.

[0012] Optionally, the double-layer flexible interconnection loss includes a full life cycle comprehensive flexible interconnection loss and a single typical running working condition flexible interconnection loss.

[0013] Optionally, each running typical working condition in the running typical working condition scenario library is traversed, and the sensitive area weight adaptive adjuster is used for adaptive adjustment of the sensitive area weight to obtain a weight updated running typical working condition scenario library; the adaptive control strategy generator is used for strategy analysis on the weight updated running typical working condition in the weight updated running typical working condition scenario library and the initial flexible interconnection scheme to obtain the running typical working condition control strategy library.

[0014] Optionally, real-time running working conditions are matched with running typical working conditions in the running typical working condition scenario library in terms of similarity, and the running typical working condition corresponding to the maximum similarity value is taken as a matching result.

[0015] In a second aspect, the application further provides a medium-voltage network flexible interconnection system for executing the medium-voltage network flexible interconnection method in the first aspect, wherein the medium-voltage network flexible interconnection system comprises: a typical working condition extraction module configured to obtain a historical load data set, a historical energy storage data set and a historical running data set of a target medium-voltage distribution network, perform running typical working condition extraction, and construct a running typical working condition scenario library; a flexible interconnection scheme identification module configured to take the installation position and installation capacity of the flexible interconnection device as decision variables, take the minimum double-layer flexible interconnection loss as a decision constraint, and perform flexible interconnection scheme identification in combination with the running typical working condition scenario library to obtain an initial flexible interconnection scheme; a control strategy generation module configured to introduce a local sensitive area weight adaptive adjuster, perform adaptive control strategy generation on the initial flexible interconnection scheme in combination with the running typical working condition scenario library to obtain a running typical working condition control strategy library; and a strategy matching module configured to obtain real-time running working conditions of the target medium-voltage distribution network, match the real-time running working conditions with the running typical working condition scenario library, and control the matching running typical working condition control strategy in the running typical working condition control strategy library according to a matching result to complete flexible interconnection.

[0016] One or more technical solutions provided in the application have at least the following beneficial effects:

[0017] The historical load data set, the historical energy storage data set and the historical operation data set of the target medium-voltage distribution network are acquired, operation typical working condition extraction is performed, and an operation typical working condition scene library is constructed; the installation position and the installation capacity of the flexible interconnection device are taken as decision variables, the minimum double-layer flexible interconnection loss is taken as a decision constraint, the flexible interconnection scheme identification is performed in combination with the operation typical working condition scene library, and an initial flexible interconnection scheme is obtained; a local sensitive area weight adapter is introduced, the adaptability control strategy generation is performed on the initial flexible interconnection scheme in combination with the operation typical working condition scene library, and an operation typical working condition control strategy library is obtained; the real-time operation working condition of the target medium-voltage distribution network is acquired, the real-time operation working condition is matched with the operation typical working condition scene library, and the matching operation typical working condition control strategy in the operation typical working condition control strategy library is called according to the matching result to perform control, and the flexible interconnection is completed. That is, the operation typical working condition scene library is constructed, the installation position and the capacity of the flexible interconnection device are taken as decision variables, the scheme identification is performed in combination with the operation typical working condition scene library, the flexible interconnection device can flexibly adjust its working state under different working conditions to adapt to the change of the power grid, the local sensitive area weight adapter is introduced, the dynamic adaptability control strategy is generated for the actual operation state of the power grid, the current working condition is accurately identified, and the matching control strategy is called to ensure that the power grid can realize effective control under different operation states and improve the stability of the power grid.

[0018] The above description is only a summary of the technical scheme of the present application. In order to more clearly understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical scheme in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by those skilled in the art without creating laborious work on the basis of the provided drawings.

[0020] Figure 1 It is a flowchart of the medium-voltage network flexible interconnection method in the present application.

[0021] Figure 2 It is a structural schematic diagram of the medium-voltage network flexible interconnection system in the present application.

[0022] Reference signs: typical operating condition extraction module 11, flexible interconnection scheme identification module 12, control strategy generation module 13, strategy matching module 14. DETAILED DESCRIPTION

[0023] The present application provides a medium-voltage grid flexible interconnection method and system, which solves the technical problem in the prior art that the control of the fixed-structure distribution grid under different operating conditions is not flexible enough due to the complex and variable operation state of the power grid, thereby affecting the stability of the distribution grid. By constructing an operating typical condition scenario library, taking the installation position and capacity of the flexible interconnection device as the decision variable, and combining the operating typical condition scenario library for scheme identification, the flexible interconnection device can flexibly adjust its working state under different conditions to adapt to the changes of the power grid. A local sensitive area weight adapter is introduced to generate a dynamic adaptive control strategy for the actual operation state of the power grid, accurately identify the current condition, and call the matching control strategy to ensure that the power grid can realize effective control under different operating states and improve the stability of the power grid.

[0024] Hereinafter, the technical solutions in the present application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application. In addition, it should be noted that, for convenience of description, only parts related to the present application are shown in the drawings, not all.

[0025] Embodiment one, please refer to the accompanying Figure 1 The present application provides a medium-voltage grid flexible interconnection method, wherein the medium-voltage grid flexible interconnection method is executed by a medium-voltage grid flexible interconnection system, and the medium-voltage grid flexible interconnection method specifically includes the following steps:

[0026] Obtain a historical load data set, a historical energy storage data set and a historical operation data set of a target medium-voltage distribution grid, extract operating typical conditions, and construct an operating typical condition scenario library.

[0027] Further, the application further includes the following steps: performing time sequence alignment and missing value completion processing on the historical load data set, the historical energy storage data set and the historical operation data set to construct a comprehensive operation data set; performing single-peak mode constraint peak value detection on the comprehensive operation data set to determine a key operation time set; respectively taking the key operation time set as the center, performing topological division on the comprehensive operation data set according to a preset power flow statistical window to determine an operation topological segment set and an operation topological segment feature set; and performing clustering on the operation topological segment set according to a preset clustering scale based on the operation topological segment feature set to construct an operation typical working condition scenario library.

[0028] Further, the application further includes the following steps: performing time sequence alignment and missing value completion processing on the historical load data set, the historical energy storage data set and the historical operation data set to construct a comprehensive operation data set; performing single-peak mode constraint peak value detection on the comprehensive operation data set to determine a key operation time set; respectively taking the key operation time set as the center, performing topological division on the comprehensive operation data set according to a preset power flow statistical window to determine an operation topological segment set and an operation topological segment feature set; and performing clustering on the operation topological segment set according to a preset clustering scale based on the operation topological segment feature set to construct an operation typical working condition scenario library.

[0029] Further, the application further includes the following steps: performing time sequence alignment and missing value completion processing on the historical load data set, the historical energy storage data set and the historical operation data set to construct a comprehensive operation data set; performing single-peak mode constraint peak value detection on the comprehensive operation data set to determine a key operation time set; respectively taking the key operation time set as the center, performing topological division on the comprehensive operation data set according to a preset power flow statistical window to determine an operation topological segment set and an operation topological segment feature set; and performing clustering on the operation topological segment set according to a preset clustering scale based on the operation topological segment feature set to construct an operation typical working condition scenario library.

[0030] Further, the application further includes the following steps: performing time sequence alignment and missing value completion processing on the historical load data set, the historical energy storage data set and the historical operation data set to construct a comprehensive operation data set; performing single-peak mode constraint peak value detection on the comprehensive operation data set to determine a key operation time set; respectively taking the key operation time set as the center, performing topological division on the comprehensive operation data set according to a preset power flow statistical window to determine an operation topological segment set and an operation topological segment feature set; and performing clustering on the operation topological segment set according to a preset clustering scale based on the operation topological segment feature set to construct an operation typical working condition scenario library.

[0031] In particular, medium-voltage distribution network generally refers to the distribution system with voltage level between 1 kV and 35 kV, which is the transition level from the main power grid to the low-voltage user distribution. The role of medium-voltage distribution network is to distribute power from the substation to each power consumption area, connecting the power transmission between the main grid and the user. Obtain all important data sets of the target medium-voltage distribution network in the historical period, including historical load data set, historical energy storage data set and historical operation data set. The historical load data set is the real-time data of the power load of each region in the distribution network in a certain historical period, which reflects the power demand of the power grid at different times, seasons or events. The historical energy storage data set is the detailed data of the storage and release of energy by energy storage devices (such as batteries, super capacitors, etc.) in historical operation, including charging, discharging cycle, power change and other information. The historical operation data set is the historical data of the operation state of the equipment and system of the distribution network, usually including device state (operation condition of switches, transformers, circuit breakers, etc.), voltage, current, power flow and other data.

[0032] In order to ensure the timeliness and consistency of the data, the historical load data set, the historical energy storage data set and the historical operation data set are time-aligned to ensure that these data are arranged according to the same time interval and eliminate the difference in time. For missing data caused by equipment problems or other reasons, interpolation method or regression method based on adjacent data is used for completion. Time alignment is to synchronize and align different sources of data (load data, energy storage data, operation data) according to time sequence to ensure that different data sets can be compared and analyzed at the same time point. In the actual data collection process, data may be missing due to equipment failure, communication problems and other reasons. Missing value completion refers to filling the missing data by interpolation, regression and other methods to ensure the integrity of the data set. The comprehensive operation data set is the data set after time alignment and missing value completion, which contains complete information of historical load, energy storage and distribution network operation state.

[0033] Traverse all data points of the comprehensive operation data set to find those time points that show great fluctuations in a period of time. The maximum fluctuation refers to the local fluctuation of the whole, such as the overall fluctuation of 3 data in the comprehensive operation data. For example, the data in a period of time (such as 3 data points) shows a significant change trend, such as the load or current rises rapidly from a low value and then drops rapidly, which is regarded as a local maximum fluctuation. Extract all local maximum fluctuation values from the comprehensive operation data set to obtain the local maximum fluctuation comprehensive operation data set.

[0034] The local fluctuation maximum comprehensive operation data set is taken as the center, and is extended to both sides to find the corresponding single-peak mode interval. The single-peak mode interval is a time interval that takes the local fluctuation maximum point as the center and contains the complete rising and falling stages of the fluctuation process. In this interval, the data change trend generally presents a mountain peak shape, that is, first rising and then falling (or first falling and then rising), and there is only one main peak or valley. The single-peak here describes the main trend of data change in the interval, and small burrs or fluctuations are allowed.

[0035] For each local fluctuation maximum point in the local fluctuation maximum comprehensive operation data set, take its occurrence time as the starting point, trace back a certain time (such as 5-10 minutes according to experience or preset parameters), find the time when the fluctuation starts to become significant; at the same time, trace back the same or slightly longer time, find the time when the fluctuation tends to be flat. The time period between the two time points is defined as a single-peak mode interval, which contains the process from the beginning of the fluctuation, to the peak, and then to the basic recovery. Take this interval and its corresponding comprehensive operation data (i.e. all data points in the interval) as a whole, and store it in the local fluctuation maximum comprehensive operation data interval set.

[0036] The preset interval width threshold is the maximum width of the time interval when screening the local fluctuation maximum. For example, only the intervals with duration greater than or equal to 5 minutes or less than or equal to 30 minutes are retained, and the intervals that are too short (may be just noise) or too long (may have contained multiple independent fluctuations) are filtered out. The preset peak amplitude threshold is the threshold for screening the fluctuation amplitude of the local fluctuation maximum. Only those fluctuations with an amplitude exceeding the set value are considered valid. For example, only the intervals with a peak-to-peak amplitude exceeding 10% or an absolute value exceeding 50 kW are retained, and the fluctuations with a small amplitude (may not be significant) are filtered out. In order to focus on the key fluctuation processes that have a substantial impact on the operation of the power grid, the set of local fluctuation maximum comprehensive operation data intervals needs to be screened, and two screening criteria, the preset interval width threshold and the preset peak amplitude threshold, are set. Each interval in the set of local fluctuation maximum comprehensive operation data intervals is traversed, and its width is checked to see if it is within the threshold range, and the peak-to-peak amplitude of the interval relative to the load change at the start or end of the interval is checked to see if it exceeds the threshold. Only intervals that meet both conditions are retained and stored in the screened local fluctuation maximum comprehensive operation data interval set, and intervals that do not meet the conditions are discarded. For example, assume that the set of local fluctuation maximum comprehensive operation data intervals has the following three intervals: Interval A: width = 3 minutes, peak amplitude = 30 kW (relative to the start of the interval); Interval B: width = 25 minutes, peak amplitude = 45 kW; Interval C: width = 35 minutes, peak amplitude = 60 kW. Set the preset interval width threshold to [5, 40] minutes and the preset peak amplitude threshold to ≥ 30 kW. Interval A: width 3 < 5, does not meet; even if the amplitude meets, it is screened out; Interval B: width 25 is within [5, 30], amplitude 45 ≥ 30, meets, and is retained; Interval C: width 35 is within [5, 30], amplitude 60 ≥ 30, is retained. At this time, Interval B and Interval C both meet the conditions and are retained in the screened local fluctuation maximum comprehensive operation data interval set. In practical applications, the thresholds need to be adjusted according to the characteristics of the power grid and the analysis goals.

[0037] After the screening is completed, the time corresponding to the local fluctuation maximum comprehensive operation data corresponding to the screening local fluctuation maximum comprehensive operation data interval set is considered as the key moment when the power grid operation state changes significantly, that is, the accurate time point identified as the local fluctuation maximum in each interval after screening is added to the key operation time set, and these time points that need to be analyzed are clearly marked. Traverse each element in the screening local fluctuation maximum comprehensive operation data interval set (that is, a screened interval and its data), find the exact time when the local fluctuation maximum point recorded in the interval occurs, and then add this time to the key operation time set. If the same time is identified multiple times due to the overlap or similarity of multiple adjacent intervals, it may need to be processed for duplicate removal. The key operation time set is a set of time points identified as having important significance during the operation of the power grid after screening and analysis, which are usually the time points of key changes or abnormal fluctuations in the operation of the power grid, which may affect the stability or efficiency of the power grid.

[0038] The preset power flow statistical window is a fixed time window set when extracting distribution network data, which is used for statistical analysis of distribution network operation data. The size (such as 5 minutes, 1 hour, etc.) and content (such as load, current, voltage, etc. Data) of the window can be set according to the needs in practical application. The function of the preset power flow statistical window is to extract detailed operation data within a certain period of time before and after a key operation time, not only including traditional power flow data (such as line current, voltage, power), but also including device state (such as switch state, transformer tap position), external characteristics (such as weather data, load type information) and snapshot of power grid topology (i.e. The overall picture of the electrical connection structure and device state of the distribution network in this time period). By analyzing the data in this window, a series of statistical characteristics can be calculated, such as peak intensity (maximum load or power), change rate (speed of load or power change), duration (time of maintaining a certain state or level), over-limit duration (time length of voltage, current, etc. Out of the safe range) and network loss estimation (estimated line loss in this time period) and the like.

[0039] First, the size of the preset power flow statistical window is determined, such as being set to ± 15 minutes. Then, each time point in the set of key operation time points is taken as the center point on the time axis. Next, all relevant data in the entire time period from the preset window time (such as 15 minutes) before the center time to the preset window time (such as 15 minutes) after the center time are found and extracted from the set of comprehensive operation data, including but not limited to: node voltages, line currents, power flows, switch states, transformer tap positions, real-time values of loads and energy storage, weather information, and a snapshot of the topology connection relationship of the power grid at the time. A running topology segment containing detailed operation information in the period before and after each key operation time is generated for each key operation time, like a snapshot set in the process of power grid operation, each snapshot focusing on an important time point and its surrounding dynamic process, thereby obtaining a set of running topology segments. For example, assume that there are two time points in the set of key operation time points: time point A is 8:00, and time point B is 14:30. The preset power flow statistical window is ± 15 minutes. For time point A (8:00), the data in the period from 7:45 to 8:15 is extracted. Assume that the extracted data segment shows that: from 7:45 to 8:00, the load gradually increases, reaches a peak of 1500 kW at 8:00, and from 8:00 to 8:15, the load slightly falls to 1450 kW; the energy storage system starts charging at 7:50 and stops charging at 8:10; a certain tie switch briefly acts at 8:05; the topology structure of the power grid remains stable (without faults or planned operations) in the period, including the load change curve, energy storage state change, switch action record, and topology snapshot. For time point B (14:30), the data in the period from 14:15 to 14:45 is extracted. Assume that the extracted data segment shows that: from 14:15 to 14:25, the load is stable at 1000 kW; at 14:25, a rapid fluctuation occurs, the load reaches a peak of 1800 kW at 14:28, and then falls to 950 kW at 14:35; the energy storage system quickly discharges to provide support during the fluctuation; a short voltage excursion (14:28-14:32) occurs in a certain area; the topology structure of the power grid also remains stable in the period, capturing a load fluctuation and voltage excursion event.

[0040] The feature recognition is performed on the set of operation topology segments extracted from the power flow statistical window, and the key features of each topology segment in the power grid operation process are identified, which can distinguish the differences between different segments and reflect the core operation state of the segment. A set of feature extraction rules or calculation methods are defined in advance, such as calculating the maximum load, minimum load and average load in the segment; calculating the maximum change rate of load or power; counting the number of device states (such as switch action) in the segment; calculating the number and duration of voltage or current out-of-limit; estimating the total network loss in the segment; extracting the charging and discharging behavior characteristics of the energy storage system (such as maximum charging and discharging power and duration); extracting the power flow characteristics of the key line, etc. Each segment in the set of operation topology segments is traversed. For the segment being processed, the pre-defined feature extraction rules are applied to calculate the corresponding feature values from the detailed data included in the segment. For example, for segment A (corresponding to time 8:00), the peak load is calculated as 1500 kW, the average load is calculated as 1475 kW, the maximum change rate is calculated as 50 kW / min, the energy storage charging duration is calculated as 10 minutes, the network loss is estimated as 25 kW, and there is no out-of-limit, etc. For segment B (corresponding to time 14:30), the peak load is calculated as 1800 kW, the average load is calculated as 1150 kW, the maximum change rate is calculated as 300 kW / min, the energy storage discharging duration is calculated as 5 minutes, the network loss is estimated as 30 kW, and the voltage out-of-limit duration is calculated as 4 minutes, etc. These calculated feature values are organized into a feature vector (such as [1500, 1475, 50, 10, 25, 0] and [1800, 1150, 300, 5, 30, 4]). Finally, the feature vectors corresponding to all segments are collected to form a topology segment feature set. The topology segment feature set is a set composed of feature vectors corresponding to each operation topology segment. Each feature vector contains all the identified feature values extracted from the corresponding segment.

[0041] The preset clustering scale is the fineness or granularity of the clustering grouping when performing clustering analysis, including distance threshold (such as when the distance between two feature vectors is less than a certain set value), similarity threshold (such as when the similarity between two feature vectors is greater than a certain set value), clustering algorithm parameters (such as the number of clusters K in the K-means algorithm), etc. The clustering scale determines the degree of refinement of the clustering result. A smaller clustering scale will result in more and smaller clusters, while a larger clustering scale will produce fewer but larger clusters. According to the preset clustering scale, all the running topology segment feature sets are clustered, and topology segments with similar features are grouped into the same class, usually by some similarity measure (such as Euclidean distance) to measure the similarity between segments. The granularity of clustering is controlled by the preset clustering scale. If the clustering scale is large, the clustering result will be more rough, and the number of clustered segments will be less; if the clustering scale is small, the clustering will be more refined, and the number of clusters will be more. For example, using the K-means algorithm, using the K-means clustering algorithm, and presetting the clustering scale (number of clusters K) as 4, all feature vectors are divided into 3 clusters, so that the vectors within each cluster are as similar as possible, while the vectors between different clusters are as different as possible. Cluster 1 feature set: contains 30 feature vectors, representing high load, low fluctuation, and energy storage charge / discharge balance; Cluster 2 feature set: contains 25 feature vectors, representing medium load, medium fluctuation, and energy storage mainly charging; Cluster 3 feature set: contains 35 feature vectors, representing low load, high fluctuation, and energy storage mainly discharging; Cluster 4 feature set: contains 10 feature vectors, representing extremely high load, high fluctuation, and energy storage fast discharging with over-limit.

[0042] According to the multiple clustering running topology segment feature sets, the running topology segment set is mapped and clustered to obtain multiple mapped and clustered running topology segment sets. In short, according to the clustering result of the features of each running topology segment, the original data level is mapped back, all running topology segments are traversed to find their corresponding feature vectors, it is checked which cluster feature set the feature vector belongs to, and then the original topology segment is put into the corresponding mapped and clustered running topology segment set. Mapping and clustering is to map certain feature sets (such as running topology segment feature sets) to a certain clustering model, i.e. to assign each topology segment to the formed cluster according to its features, to obtain multiple mapped and clustered running topology segment sets. The mapped and clustered running topology segment set is obtained by re-grouping the original running topology segment set according to the cluster result to which their respective feature vectors belong. For example, if the feature vector of an original segment A belongs to cluster 1 feature set, then segment A should be put into mapped and clustered running topology segment set 1; if the feature vector of segment B belongs to cluster 2 feature set, then segment B should be put into mapped and clustered running topology segment set 2.

[0043] The number of segments in each of the plurality of mapping cluster running topology segment sets is counted respectively, i.e. the number of topology segments contained in each of the plurality of mapping cluster running topology segment sets, to determine the proportion of each cluster in all topology segments. By counting the number of segments of each cluster, the statistical result is divided by the total number of the plurality of mapping cluster running topology segment sets to obtain a plurality of probability coefficients representing the frequency or probability of each typical working condition appearing in the historical data. The probability coefficient is the proportion of each cluster in all clusters, representing the proportion of each cluster in the total data. For example, if set 2 has 25 segments and the total number of segments is 100, the probability coefficient of set 2 is 25 / 100=25%.

[0044] The mean of the plurality of mapping clustering operation topology segment sets is calculated to obtain a plurality of operation typical working conditions, the mean refers to the average of the characteristic values of all segments in each cluster, representing the typical operation state in the cluster. Each calculated operation typical working condition (mean vector) is paired with its corresponding probability coefficient, and these paired information is stored to form an operation typical working condition scenario library. The operation typical working condition scenario library refers to the set of all typical working conditions obtained through clustering analysis, which represents the common operation state of the power grid under different conditions and contains a plurality of entries, each entry consisting of an operation typical working condition (its mean characteristic vector) and its corresponding probability coefficient. For example, typical working condition 1 (corresponding to set 1): assuming its mean characteristic vector is [peak load 1450 kW, average load 1350 kW, maximum load change rate 2.5 kW / min, energy storage charging and discharging time 8 min, network loss estimation 28 kW, over-limit duration 1 min]; typical working condition 2 (corresponding to set 2): assuming its mean characteristic vector is [peak load 1200 kW, average load 950 kW, maximum load change rate 5.0 kW / min, energy storage charging time 12 min, network loss estimation 22 kW, over-limit duration 0 min]; typical working condition 3 (corresponding to set 3): assuming its mean characteristic vector is [peak load 800 kW, average load 650 kW, maximum load change rate 15.0 kW / min, energy storage discharging time 7 min, network loss estimation 18 kW, over-limit duration 3 min]; typical working condition 4 (corresponding to set 4): assuming its mean characteristic vector is [peak load 1900 kW, average load 1700 kW, maximum load change rate 30.0 kW / min, energy storage discharging time 5 min, network loss estimation 35 kW, over-limit duration 4 min], the typical working condition is associated with its probability coefficient to form a scenario library entry: entry 1 {typical working condition [1450, 1350, 2.5, 8, 28, 1], probability coefficient 0.3}, entry 2 {typical working condition [1200, 950, 5.0, 12, 22, 0], probability coefficient 0.25}, entry 3 {typical working condition [800, 650, 15.0, 7, 18, 3], probability coefficient 0.35}, entry 4 {typical working condition [1900, 1700, 30.0, 5, 35, 4], probability coefficient 0.1}, forming the operation typical working condition scenario library of the target medium voltage distribution network.

[0045] The peak value detection effectively identifies the time nodes of great significance in the power grid, the topology division and feature extraction clearly define the operation state of the power grid in different time periods, and the clustering analysis can simplify the complex operation state of the power grid into several typical working conditions, and a typical working condition scenario library is constructed according to the typical working conditions.

[0046] The installation position and installation capacity of the flexible interconnection device are taken as decision variables, and minimum double-layer flexible interconnection loss is taken as a decision constraint to identify a flexible interconnection scheme in combination with the library of typical operation condition scenarios to obtain an initial flexible interconnection scheme.

[0047] Further, the application further includes the following steps: taking the installation position and installation capacity of the flexible interconnection device as decision variables, identifying a flexible interconnection scheme based on the library of typical operation condition scenarios respectively to obtain a set of independent flexible interconnection schemes; taking minimum double-layer flexible interconnection loss as a decision constraint to identify a scheme reliability coefficient of the set of independent flexible interconnection schemes respectively to obtain a set of scheme reliability coefficients; and taking an independent flexible interconnection scheme corresponding to the maximum value in the set of scheme reliability coefficients as the initial flexible interconnection scheme.

[0048] Further, the application further includes the following steps: the double-layer flexible interconnection loss includes a comprehensive flexible interconnection loss in a whole life cycle and a single typical operation condition flexible interconnection loss.

[0049] Specifically, from the perspective of grid upgrading, flexible interconnection technology is an effective means to solve the problem. The flexible interconnection technology of the distribution network upgrades / constructs a tie-in node by using power electronic flexible interconnection devices (FID), utilizes the dynamic power flow control capability and fault isolation capability of the FID to realize flexible closed-loop operation of the distribution network, and further forms a new type of flexible distribution system. The flexible interconnection device includes an intelligent soft switch, an energy router, an intelligent power / information exchange base station, etc., and is a device capable of realizing flexible power exchange between different parts of the power grid. The installation position of the flexible interconnection device refers to the specific installation site in the distribution network, and the installation capacity refers to the capacity of the device, i.e., the power load that it can carry. The selection of the position and the capacity will affect the efficiency of the device and the flexibility of the grid operation.

[0050] The installation position and installation capacity of the flexible interconnection device are taken as decision variables, and minimum double-layer flexible interconnection loss is taken as a decision constraint to identify a flexible interconnection scheme in combination with the library of typical operation condition scenarios to obtain an initial flexible interconnection scheme.

[0051] The double-layer flexible interconnection loss is the loss generated by the flexible interconnection device under different operating states, which is usually divided into two parts: the full life cycle comprehensive flexible interconnection loss and the single typical operating condition flexible interconnection loss. The full life cycle comprehensive flexible interconnection loss is the total loss of the flexible interconnection device in the entire life cycle, including the energy loss in the stages of device manufacturing, operation, maintenance, etc. The single typical operating condition flexible interconnection loss is the energy loss of the flexible interconnection device under a certain specific operating condition. For example, under high load conditions, the device may have a larger loss. For each flexible interconnection scheme, the full life cycle comprehensive flexible interconnection loss is calculated by the device's operating history, maintenance records, device efficiency, etc. For each typical operating condition, the single typical operating condition flexible interconnection loss under that condition is calculated. The full life cycle comprehensive flexible interconnection loss and the single typical operating condition flexible interconnection loss are weighted and summed to obtain the reliability coefficient of each scheme. The minimum double-layer flexible interconnection loss is used as the decision constraint to evaluate each scheme in the independent flexible interconnection scheme set. The purpose of the evaluation is to calculate the reliability coefficient of each scheme, which reflects the reliability level of the scheme under the constraint of minimizing the loss. By comparing the reliability coefficients of different schemes, the optimal flexible interconnection scheme is identified. For example, assuming that the annual loss of scheme A is 500 kWh, the service life of the device is 20 years, and the full life cycle loss is 10000 kWh, under high load conditions, the device loss of scheme A is 600 kWh, and the single typical operating condition loss is 600 kWh, the total loss of scheme A is 10600 kWh, the stability evaluation score of scheme A is 0.9 (indicating that scheme A has good stability under high load conditions and strong device recovery ability), and the reliability coefficient of scheme A is 0.849. The annual loss of scheme B is 450 kWh, the service life of the device is 20 years, the full life cycle loss is 9000 kWh, under high load conditions, the device loss of scheme B is 550 kWh, and the single typical operating condition loss is 550 kWh, the total loss of scheme B is 9550 kWh, the stability evaluation score of scheme B is 0.85 (compared with scheme A, scheme B has slightly worse stability under high load conditions and weaker recovery ability), and the reliability coefficient of scheme B is 0.89. Scheme B has a slightly higher reliability coefficient, which means it may perform more reliably under the same operating conditions, although its full life cycle loss is slightly lower.

[0052] The scheme with the highest reliability coefficient in the scheme reliability coefficient set is selected as the initial flexible interconnection scheme, which represents the configuration that can best ensure the stable operation of the power grid under the current power grid operating conditions. The initial flexible interconnection scheme has the highest reliability among all considered schemes, i.e., it can most effectively improve the stability and reliability of the power grid while meeting the minimum loss minimization constraint. For example, the reliability coefficient of scheme A is 0.95, the reliability coefficient of scheme B is 0.9, and the reliability coefficient of scheme C is 0.85, so scheme A will be selected as the initial flexible interconnection scheme. By optimizing the installation location and capacity of the flexible interconnection device, and based on the operation typical working condition scenario library, scheme identification, loss calculation and reliability evaluation are performed to obtain a set of optimal flexible interconnection schemes, and the scheme with the highest reliability coefficient is selected as the initial flexible interconnection scheme to ensure the best performance of the power grid under different operating conditions.

[0053] A local sensitive area weight adapter is introduced to generate adaptive control strategies for the initial flexible interconnection scheme based on the operation typical working condition scenario library, thereby obtaining an operation typical working condition control strategy library.

[0054] Further, the present application further includes the following steps: traversing each operation typical working condition in the operation typical working condition scenario library, and using the local sensitive area weight adapter to adaptively adjust the weight of the sensitive area to obtain a weight updated operation typical working condition scenario library; and using an adaptive control strategy generator to analyze the weight updated operation typical working condition in the weight updated operation typical working condition scenario library and the initial flexible interconnection scheme to obtain the operation typical working condition control strategy library.

[0055] In particular, the local sensitive area weight adapter is used to dynamically adjust the weight of a specific area or device under different operating conditions during the operation of the power grid. According to the load fluctuation of the local area in the power grid, the change of the device state and other factors, the weight of the area is adaptively adjusted to ensure the balance and stability of the distribution network. The local sensitive area weight adapter can adjust the priority of each area in the distribution network according to real-time load, voltage change and device operating state information. Different areas of the power grid may experience different degrees of load fluctuation, voltage fluctuation or device failure during operation, which will affect the stability of the power grid operation. The fluctuation of the load in a certain area of the power grid may affect the priority of the power grid operation in that area. If the load of a certain area fluctuates greatly, the weight of that area may increase to prioritize adjustment and optimization. If some power devices are in an abnormal operating state (such as overload, failure, etc.), the weight of the local sensitive area will increase accordingly, so that these problem areas can be prioritized. In some areas with unstable voltage, the weight of the area is increased when the voltage fluctuation is large, so that control and optimization can be prioritized. By introducing the local sensitive area weight adapter, the weight of each area can be dynamically adjusted according to the real-time state of the power grid to ensure the stability and reliability of the overall operation of the power grid.

[0056] During the traversal of the typical operating condition scenario library, for each operating typical condition, the local sensitive area weight adapter is used to adaptively adjust the weight of the sensitive area. For each typical condition, data analysis is used to identify sensitive areas that are more affected by load fluctuations, voltage fluctuations, device failures, etc. According to the identified sensitive areas, the local sensitive area weight adapter is used to adaptively adjust the weight of these areas. If a certain area experiences large fluctuations or device failures, the local sensitive area weight adapter will increase the weight of that area, so that it will receive more attention in subsequent control. After weight adaptive adjustment, the updated operating typical condition scenario library reflects the adjustment results of each area. The weight of the sensitive area in each condition scenario will affect the subsequent optimization and scheduling strategy. Sensitive areas are areas in the power grid that are more sensitive to certain operating conditions (such as load, device state, etc.), and the load, current, voltage, etc. of the sensitive area usually fluctuate greatly, which may affect the stability of the entire power grid.

[0057] The dynamic weight adjustment mechanism is applied to the typical operating conditions abstracted from historical data. Although the typical operating conditions are based on the average or representative state obtained from historical data statistics, the vulnerability distribution of the power grid under different operating conditions may be different. For example, under peak load conditions, all regions may face power supply pressure, and the weight of sensitive regions may be generally higher; but under the condition that a large industrial equipment in a certain region starts or stops, the weight of the region may abnormally increase. Each typical operating condition in the scenario library is traversed. For each operating condition, the local sensitive region weight adapter introduced earlier is used to simulate or calculate what the sensitive weight of each region should be under the conditions of that specific operating condition. The local sensitive region weight adapter will infer the weight distribution according to the characteristics of the operating condition, such as load level, equipment state estimation, etc. For example, for a typical operating condition representing the summer peak, the local sensitive region weight adapter may assign a higher base weight to all regions, especially those regions that are historically prone to overload or connect important users in the summer. After completing the weight adjustment for all typical operating conditions, the original operating condition characteristics are bound with the new weight information to form a new data set, i.e. the weight updated operating typical condition scenario library.

[0058] The adaptive control strategy generator generates specific control strategies by analyzing the operating condition scenarios of the power grid, and adaptively adjusts according to the current operating state of the power grid to ensure stable operation of the power grid. The adaptive control strategy generator is a system that automatically generates or adjusts control instructions (such as switch state, transformer tap position, flexible interconnection device control parameters, etc.) according to the current state of the power grid (including operating conditions, equipment state, sensitive region weight, etc.) and predetermined optimization objectives (such as minimum loss, highest reliability, optimal voltage qualification rate, etc.).

[0059] According to the weight-adjusted operating typical condition scenario library and the initial flexible interconnection scheme, the adaptive control strategy generator will process each typical condition in the library in turn. For each operating condition, the adaptive control strategy generator will combine the characteristics of the operating condition (such as load level, topology, power flow distribution) and the sensitive region weight information attached to it, and consider the installation location and capacity of the devices in the initial flexible interconnection scheme, to analyze and decide, find one or a group of control strategies, so that under the specific operating condition, using the flexible interconnection scheme, the preset optimization objectives (such as maximizing the power supply reliability of sensitive regions under the constraint of loss) or optimizing the voltage distribution can be best met. Control strategies may include switching instructions of intelligent soft switches, ratio adjustment instructions of power electronic transformers, power distribution instructions of tie lines, etc. For each typical operating condition, the adaptive control strategy generator outputs one or more recommended control strategies. These control strategies are associated with their corresponding typical operating conditions (including weight information) and stored, which constitutes the operating typical condition control strategy library.

[0060] By introducing a local sensitive area weight adapter and combining an adaptive control strategy generator, the real-time operating conditions of the power grid are adaptively adjusted and optimized, a typical operating condition control strategy library is established, each strategy is tailored for a specific operating condition (considering the sensitive area weight) and a specific flexible interconnection scheme, and the control of the power grid can be transformed from a one-size-fits-all or extensive approach to a refined and adaptive approach. When the actual operating state of the power grid is identified by the monitoring system as being close to a certain typical operating condition, the corresponding control strategy in the library is quickly retrieved and executed, greatly shortening the decision-making time and improving the timeliness and accuracy of the control, significantly improving the stability and flexibility of the power grid under various operating conditions, especially when dealing with complex and variable loads and distributed power output, better guaranteeing power supply quality and reliability.

[0061] The real-time operating condition of the target medium-voltage distribution network is obtained, the real-time operating condition is matched with the typical operating condition scenario library, and a matching typical operating condition control strategy in the typical operating condition control strategy library is retrieved according to the matching result for control, and flexible interconnection is completed.

[0062] Further, the present application further comprises the following steps: matching the real-time operating condition with the similarity of the typical operating condition in the typical operating condition scenario library, and taking the typical operating condition corresponding to the maximum similarity as the matching result.

[0063] Specifically, the real-time operating condition of the target medium-voltage distribution network at the current time is obtained, including important information such as the load, voltage, current, device state, and power flow of the power grid. The real-time operating condition is the actual operating state of the medium-voltage distribution network at the current time or within a short period of time, reflecting the actual operating condition of the power grid at a specific time period, which may be affected by load fluctuations, equipment failures, and other factors. The obtained real-time condition is matched with the similarity of each condition in the typical operating condition scenario library. The Euclidean distance between the real-time condition and the feature data of each typical condition is calculated. The smaller the distance, the more similar the two conditions. By calculating the similarity value, the typical operating condition corresponding to the maximum similarity is determined as the matching result. This condition is the most similar operating condition to the current power grid state. For example, the load of feeder A is 1.2 MW (load rate 80%), the load of feeder B is 0.9 MW (load rate 60%), and the load of feeder C is 0.7 MW (load rate 40%), the distance from condition 1 (high load, A0.6, B0.3, C0.1) is 0.45, the distance from condition 2 (low valley, A0.4, B0.3, C0.3) is 1.20, and the distance from condition 3 (A heavy load, B light load, C medium) is 0.35. The distance between the real-time condition and condition 3 is the smallest (0.35), indicating that they are most similar in features. Therefore, condition 3 is determined as the matching result.

[0064] According to the matching result, the corresponding control strategy is retrieved from the typical operating condition control strategy library, the instructions therein are executed, the power grid is dynamically adjusted and controlled through the flexible interconnection device, and flexible operation of the power grid is realized. For example, if the typical operating condition is a high load state, the control strategy can include adjusting the output power of the flexible interconnection device, enabling a backup power source, or reconfiguring the load, etc. By executing the selected control strategy, flexible interconnection is achieved, i.e., through flexible power scheduling, load distribution, and device control, the stability and efficient operation of the power grid are ensured. By matching the real-time operating condition with the typical operating condition scenario library, the current operating state of the power grid is identified, and the most suitable control strategy is selected. Retrieving and executing the control strategy in the typical operating condition control strategy library ensures efficient operation of the power grid under different operating conditions, especially through dynamic adjustment and optimization of the power grid by the flexible interconnection device, which helps to improve the stability, response speed, and energy efficiency of the power grid.

[0065] In summary, the medium voltage grid flexible interconnection method provided by the present application has the following beneficial effects:

[0066] By obtaining a historical load data set, a historical energy storage data set, and a historical operating data set of a target medium voltage distribution network, a typical operating condition is extracted, and a typical operating condition scenario library is constructed. The installation location and capacity of the flexible interconnection device are used as decision variables, and the minimum double-layer flexible interconnection loss is used as a decision constraint. In combination with the typical operating condition scenario library, a flexible interconnection scheme is identified to obtain an initial flexible interconnection scheme. A local sensitive area weight adapter is introduced, and in combination with the typical operating condition scenario library, an adaptive control strategy is generated for the initial flexible interconnection scheme to obtain a typical operating condition control strategy library. The real-time operating condition of the target medium voltage distribution network is obtained, the real-time operating condition is matched with the typical operating condition scenario library, and according to the matching result, the matching typical operating condition control strategy in the typical operating condition control strategy library is retrieved for control, and flexible interconnection is completed. That is, by constructing a typical operating condition scenario library, using the installation location and capacity of the flexible interconnection device as decision variables, and identifying the scheme in combination with the typical operating condition scenario library, the flexible interconnection device can flexibly adjust its working state under different operating conditions to adapt to changes in the power grid. A local sensitive area weight adapter is introduced to generate a dynamically adaptive control strategy for the actual operating state of the power grid, accurately identify the current operating condition, and retrieve the matching control strategy to ensure that the power grid can be effectively controlled under different operating conditions and improve the stability of the power grid.

[0067] Embodiment two, based on the same inventive concept as the medium voltage grid flexible interconnection method in the aforementioned embodiment one, the present application also provides a medium voltage grid flexible interconnection system, please refer to the attached Figure 2 The medium voltage grid flexible interconnection system includes:

[0068] The typical working condition extraction module 11 is configured to obtain a historical load data set, a historical energy storage data set and a historical operation data set of a target medium-voltage distribution network, perform operation typical working condition extraction, and construct an operation typical working condition scenario library; the flexible interconnection scheme identification module 12 is configured to take the installation position and installation capacity of the flexible interconnection device as decision variables, take the minimum double-layer flexible interconnection loss as a decision constraint, identify a flexible interconnection scheme in combination with the operation typical working condition scenario library, and obtain an initial flexible interconnection scheme; the control strategy generation module 13 is configured to introduce a local sensitive area weight adapter, generate an adaptive control strategy for the initial flexible interconnection scheme in combination with the operation typical working condition scenario library, and obtain an operation typical working condition control strategy library; and the strategy matching module 14 is configured to obtain a real-time operation working condition of the target medium-voltage distribution network, match the real-time operation working condition with the operation typical working condition scenario library, and control the matching operation typical working condition control strategy in the operation typical working condition control strategy library according to a matching result to complete flexible interconnection.

[0069] Further, the typical working condition extraction module 11 in the medium-voltage network architecture flexible interconnection system is further configured to: perform time sequence alignment and missing value completion processing on the historical load data set, the historical energy storage data set and the historical operation data set to construct a comprehensive operation data set; perform unimodal mode constraint peak value detection on the comprehensive operation data set to determine a key operation time set; respectively take the key operation time set as the center, and perform topological division on the comprehensive operation data set according to a preset power flow statistical window to determine an operation topological segment set and an operation topological segment feature set; and perform clustering on the operation topological segment set according to a preset clustering scale based on the operation topological segment feature set to construct an operation typical working condition scenario library.

[0070] Further, the typical working condition extraction module 11 in the medium-voltage network architecture flexible interconnection system is further configured to: traverse the comprehensive operation data set to extract local fluctuation maximum values to determine a local fluctuation maximum value comprehensive operation data set; take the local fluctuation maximum value comprehensive operation data set as the center, expand to both sides to form a unimodal mode interval, and obtain a local fluctuation maximum value comprehensive operation data interval set; perform screening on the local fluctuation maximum value comprehensive operation data interval set according to a preset interval width threshold and a preset peak value amplitude threshold to obtain a screened local fluctuation maximum value comprehensive operation data interval set; and add the time of the local fluctuation maximum value comprehensive operation data corresponding to the screened local fluctuation maximum value comprehensive operation data interval set to the key operation time set.

[0071] Further, the typical working condition extraction module 11 in the medium-voltage grid framework flexible interconnection system is further configured to: extract the pre and post data topologies of the comprehensive operation data set according to the preset power flow statistical window and in combination with the set of key operation time points, to determine a set of operation topology segments; and traverse the set of operation topology segments to determine a set of topology segment features.

[0072] Further, the typical working condition extraction module 11 in the medium-voltage grid framework flexible interconnection system is further configured to: aggregate the set of operation topology segment features according to a preset clustering scale to obtain a plurality of sets of clustered operation topology segment features; perform mapping clustering on the set of operation topology segments according to the plurality of sets of clustered operation topology segment features to obtain a plurality of sets of mapping clustered operation topology segments; respectively count the number of segments in the plurality of sets of mapping clustered operation topology segments, and compare the counting results with the total number of segments in the plurality of sets of mapping clustered operation topology segments to obtain a plurality of probability coefficients; calculate the mean of the plurality of sets of mapping clustered operation topology segments to obtain a plurality of operation typical working conditions, and associate the plurality of operation typical working conditions with the plurality of probability coefficients to construct an operation typical working condition scenario library.

[0073] Further, the flexible interconnection scheme identification module 12 in the medium-voltage grid framework flexible interconnection system is further configured to: take the installation location and installation capacity of a flexible interconnection device as decision variables, and respectively perform flexible interconnection scheme identification based on the operation typical working condition scenario library to obtain a set of independent flexible interconnection schemes; take the minimization of double-layer flexible interconnection loss as a decision constraint, and respectively perform scheme reliability coefficient identification on the set of independent flexible interconnection schemes to obtain a set of scheme reliability coefficients; and take the independent flexible interconnection scheme corresponding to the maximum value in the set of scheme reliability coefficients as the initial flexible interconnection scheme.

[0074] Further, the flexible interconnection scheme identification module 12 in the medium-voltage grid framework flexible interconnection system is further configured to: the double-layer flexible interconnection loss includes a comprehensive flexible interconnection loss in the whole life cycle and a flexible interconnection loss in a single typical operation working condition.

[0075] Further, the control strategy generation module 13 in the medium-voltage grid framework flexible interconnection system is further configured to: traverse each operation typical working condition in the operation typical working condition scenario library, and perform sensitive area weight self-adaptive adjustment using the local sensitive area weight adapter to obtain a weight updated operation typical working condition scenario library; and obtain an adaptive control strategy generator to respectively perform strategy analysis on the weight updated operation typical working condition in the weight updated operation typical working condition scenario library and the initial flexible interconnection scheme to obtain an operation typical working condition control strategy library.

[0076] Further, the strategy matching module 14 in the medium voltage grid flexible interconnection system is further configured to: match the real-time operation condition with the operation typical condition in the scenario library, and take the operation typical condition corresponding to the maximum similarity as the matching result.

[0077] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The foregoing Figure 1 The medium voltage grid flexible interconnection method and specific examples in Embodiment One are also applicable to the medium voltage grid flexible interconnection system in this embodiment. Based on the foregoing detailed description of the medium voltage grid flexible interconnection method, those skilled in the art can clearly know the medium voltage grid flexible interconnection system in this embodiment. Therefore, for the sake of brevity of the specification, no further detailed description is given here.

[0078] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0079] Obviously, for those skilled in the art, without departing from the principles of the present application, the present application can be improved and modified in several ways, and these improvements and modifications also fall within the protection scope of the present application.

Claims

1. A flexible interconnection method for medium-voltage grid structures, characterized in that, include: Acquire historical load data sets, historical energy storage data sets, and historical operation data sets of the target medium-voltage distribution network, extract typical operating conditions, and construct a typical operating condition scenario library; Using the installation location and capacity of the flexible interconnection device as decision variables, and minimizing the loss of the double-layer flexible interconnection as a decision constraint, the flexible interconnection scheme is identified by combining the typical operating scenario library to obtain an initial flexible interconnection scheme. By introducing a local sensitive area weighted adaptor and combining it with the typical operating condition scenario library, an adaptive control strategy is generated for the initial flexible interconnection scheme to obtain a typical operating condition control strategy library. The real-time operating conditions of the target medium-voltage distribution network are obtained, and the real-time operating conditions are matched with the typical operating condition scenario library. Based on the matching result, the matching typical operating condition control strategy in the typical operating condition control strategy library is retrieved for control to complete flexible interconnection.

2. The flexible interconnection method for medium-voltage grid structures as described in claim 1, characterized in that, Acquire historical load data sets, historical energy storage data sets, and historical operation data sets of the target medium-voltage distribution network; extract typical operating conditions; and construct a library of typical operating condition scenarios, including: The historical load data set, historical energy storage data set, and historical operation data set are time-series aligned and missing value filler is performed to construct a comprehensive operation data set. Single-peak mode constraint peak detection is performed on the comprehensive operational data set to determine the set of critical operational moments; Taking the set of key operating moments as the center, the comprehensive operating data set is topologically divided according to a preset power flow statistics window to determine the set of operating topology segments and the set of operating topology segment features; Based on the set of features of the running topology segments, the set of running topology segments is clustered according to a preset clustering scale to construct a library of typical operating conditions.

3. The flexible interconnection method for medium-voltage grid structures as described in claim 2, characterized in that, Perform single-peak pattern constraint peak detection on the comprehensive operational data set to determine the set of critical operational moments, including: The local fluctuation maxima are extracted by traversing the comprehensive operational data set to determine the comprehensive operational data set with local fluctuation maxima. Taking the comprehensive operational data set of local fluctuation maxima as the center, expand to both sides to form a single-peak mode interval, and obtain the comprehensive operational data interval set of local fluctuation maxima. The set of comprehensive operating data intervals with local fluctuation maxima is filtered according to a preset interval width threshold and a preset peak amplitude threshold to obtain a filtered set of comprehensive operating data intervals with local fluctuation maxima. Add the time corresponding to the comprehensive operating data of the local fluctuation maxima corresponding to the selected set of local fluctuation maxima to the set of key operating times.

4. The flexible interconnection method for medium-voltage grid structures as described in claim 2, characterized in that, Centered on the set of key operating moments, the comprehensive operating data set is topologically partitioned according to a preset power flow statistics window to determine the set of operating topology segments and the set of operating topology segment features, including: According to the preset power flow statistics window, and in conjunction with the set of key operating moments, the comprehensive operating data set is subjected to front and back data topology extraction to determine the set of operating topology segments; The set of running topology fragments is traversed to perform feature recognition, thereby determining the feature set of the topology fragments.

5. The flexible interconnection method for medium-voltage grid structures as described in claim 2, characterized in that, Based on the set of features of the running topology segments, the set of running topology segments is clustered according to a preset clustering scale to construct a library of typical operating scenarios, including: The running topology fragment feature set is aggregated according to a preset clustering scale to obtain multiple clustered running topology fragment feature sets; Based on the feature set of the multiple clustered running topology fragments, the set of running topology fragments is mapped and clustered to obtain multiple mapped and clustered running topology fragment sets; The number of segments in each of the multiple mapping clustering running topology segment sets is counted, and the counted results are compared with the total number of segments in the multiple mapping clustering running topology segment sets to obtain multiple probability coefficients; Calculate the mean of the multiple mapping clustering operation topology fragment sets to obtain multiple typical operating conditions, and associate the multiple typical operating conditions with multiple probability coefficients to construct the typical operating condition scenario library.

6. The flexible interconnection method for medium-voltage grid structures as described in claim 1, characterized in that, Using the installation location and capacity of the flexible interconnection equipment as decision variables, and minimizing the loss of the double-layer flexible interconnection as a decision constraint, the flexible interconnection scheme is identified by combining the aforementioned typical operating scenario library, resulting in an initial flexible interconnection scheme, including: Using the installation location and capacity of flexible interconnection devices as decision variables, flexible interconnection schemes are identified based on the aforementioned typical operating scenario library to obtain an independent set of flexible interconnection schemes. Using the minimum loss of the two-layer flexible interconnection as the decision constraint, the reliability coefficient of each of the independent flexible interconnection schemes is identified to obtain the scheme reliability coefficient set. The independent flexible interconnection scheme corresponding to the maximum value in the set of reliability coefficients of the above schemes is taken as the initial flexible interconnection scheme.

7. The flexible interconnection method for medium-voltage grid structures as described in claim 6, characterized in that, The double-layer flexible interconnect loss includes the total flexible interconnect loss over the entire life cycle and the flexible interconnect loss under a single typical operating condition.

8. The flexible interconnection method for medium-voltage grid structures as described in claim 1, characterized in that, By introducing a local sensitive area weighted adaptor and combining it with the aforementioned typical operating condition scenario library, an adaptive control strategy is generated for the initial flexible interconnection scheme, resulting in a typical operating condition control strategy library, including: Traverse each typical operating condition in the typical operating condition scenario library, and use the local sensitive area weight adaptor to adaptively adjust the sensitive area weight to obtain the weight update of the typical operating condition scenario library. An adaptive control strategy generator performs strategy analysis on the typical operating conditions for weight update and the initial flexible interconnection scheme in the typical operating condition scenario library for weight update operation, respectively, to obtain the control strategy library for the typical operating conditions.

9. The flexible interconnection method for medium-voltage grid structures as described in claim 1, characterized in that, The real-time operating conditions are matched with the typical operating conditions in the typical operating condition scenario library based on their similarity, and the typical operating condition with the maximum similarity is taken as the matching result.

10. A medium-voltage grid flexible interconnection system, characterized in that, The step for implementing the medium-voltage grid flexible interconnection method according to any one of claims 1 to 9, wherein the medium-voltage grid flexible interconnection system comprises: The typical operating condition extraction module is used to acquire the historical load data set, historical energy storage data set, and historical operation data set of the target medium-voltage distribution network, extract typical operating conditions, and build a typical operating condition scenario library. The flexible interconnection scheme identification module is used to identify the flexible interconnection scheme by taking the installation location and installation capacity of the flexible interconnection device as decision variables, the minimum loss of the double-layer flexible interconnection as the decision constraint, and combining the typical operating scenario library to obtain the initial flexible interconnection scheme. The control strategy generation module is used to introduce a local sensitive area weight adaptor, and combine it with the typical operating condition scenario library to generate an adaptive control strategy for the initial flexible interconnection scheme, thereby obtaining a typical operating condition control strategy library. The strategy matching module is used to obtain the real-time operating conditions of the target medium-voltage distribution network, match the real-time operating conditions with the typical operating condition scenario library, and retrieve the matching typical operating condition control strategy from the typical operating condition control strategy library according to the matching result to perform control and complete flexible interconnection.

Images