Flexible resource aggregation and control method and system of smart power grid

Abstract

The invention discloses a flexible resource aggregation and control method and system for a smart power grid, and the method comprises the steps: analyzing the operation state data of a novel power load, obtaining the spatial distribution characteristics of the novel power load in an operation state, and determining a candidate aggregation region; according to the power communication infrastructure data of the candidate aggregation region, constructing a target aggregation region screening model to determine a target aggregation region; converting the corresponding novel power load in the target aggregation area into equivalent impedance, and determining a resource clustering demand strategy of the target aggregation area based on the equivalent impedance; performing cooperative control on the operation parameters of the corresponding novel power load in the target aggregation area so as to match the resource clustering demand strategy; according to the method, resource configuration can be optimized by constructing the aggregation area, and the flexibility of distribution network coordination control and the stability of operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and system for aggregating and controlling flexibility resources of a smart grid. Background Art

[0002] Smart grids are advanced electrical grids that use digital communications and modern technologies to improve the efficiency, reliability and sustainability of electricity production, distribution and consumption. Current smart grids are rapidly integrating new types of electrical loads, such as electric vehicles and heat pumps, which provide tremendous flexibility and their energy storage capabilities can be used for a variety of grid support functions, such as peak load reduction, load shifting, grid constraint violation management, frequency regulation and system balancing.

[0003] However, integrating power loads into smart grids faces many challenges. On the one hand, since users' power load demands vary significantly in space, power demands in different regions and at different time periods vary, which will lead to a mismatch between power supply and demand and a decrease in the stability of the power system. On the other hand, for the small-scale and spatially distributed resources of the power system, due to their large number, wide distribution and different characteristics, smart grids face huge operational complexity in the process of data collection, processing, analysis and decision-making, and the configuration process often requires the construction of a large amount of dedicated communication infrastructure, which will greatly increase the construction cost of smart grids.

[0004] It can be seen that how to improve the flexibility of resource allocation and coordinated control of power loads in the power grid has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0005] The present invention provides a method and system for aggregating and controlling flexible resources of a smart grid, which can improve the flexibility of resource allocation and coordinated control of the power load of the grid, more accurately determine aggregation areas and strategic points, and thus optimize resource allocation.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a method for aggregating and controlling flexibility resources of a smart grid, including: Analyze the acquired operating status data of the new type of power load in the target area to obtain the spatial distribution characteristics of the new type of power load in the operating state; Determine a candidate aggregation area according to the spatial distribution characteristics, obtain power communication infrastructure data of the candidate aggregation area, and construct a target aggregation area screening model according to the power communication infrastructure data; Processing the target aggregation region screening model to determine the target aggregation region; Converting the corresponding new power load in the target aggregation area into an equivalent impedance, and determining the resource clustering demand strategy of the target aggregation area based on the equivalent impedance; The operating parameters of the corresponding new power loads in the target aggregation area are collaboratively controlled to match the resource clustering demand strategy.

[0007] Furthermore, the operating status data includes real-time power data, real-time load data and historical operating data of the new power load; The acquired operating status data of the new type of electric load in the target area is analyzed to obtain the spatial distribution characteristics of the new type of electric load in the operating state, including: Extracting features from the real-time power data to obtain a first distribution result reflecting the load density of the new power load; Comparing the real-time load data with a preset load threshold to obtain a second distribution result reflecting the load density of the new power load; Performing artificial intelligence prediction on the historical operation data to obtain a third distribution result reflecting the load density of the new power load; The first distribution result, the second distribution result and the third distribution result are integrated and analyzed to obtain the spatial distribution characteristics of the new power load in the operating state.

[0008] Further, determining a candidate aggregation area according to the spatial distribution characteristics, acquiring power communication infrastructure data of the candidate aggregation area, and constructing a target aggregation area screening model according to the power communication infrastructure data include: According to the distribution of the new type of power load in the spatial distribution feature, the acquired position in the first load area and the position of the selected power transmission node are used as candidate aggregation points, and the candidate aggregation area is constructed with the candidate aggregation points; Analyze the acquired power infrastructure data and communication infrastructure data within the candidate aggregation area to obtain the power communication infrastructure data; The target aggregation area screening model is constructed according to the power communication infrastructure data and the spatial distribution characteristics. The target aggregation area screening model is expressed by the following formula: in, It is Node to The distance between the aggregation nodes, Is the control system to the The distance between the aggregation nodes, It describes A binary decision variable for whether there is a clustering point among the nodes. is the total number of nodes in a given feeder, and They are respectively The running and installation costs associated with the aggregation point for each node, is a factor of constitute.

[0009] Furthermore, converting the corresponding new type of power load in the target aggregation area into an equivalent impedance includes: Acquire power consumption data of new power loads in the target aggregation area within a selected time period, and construct a clustering data set based on the power consumption data; Dividing the clustering data set into a number of clusters; The distances between the clusters are calculated according to a preset distance calculation formula, and the new type of power load is converted into a corresponding impedance according to the calculation result.

[0010] Furthermore, the collaborative control of the operating parameters of the corresponding new power loads in the target aggregation area includes: Monitoring the voltage and power consumption data of each new type of power load in the target aggregation area through a centralized control system of the smart grid, and determining whether the target aggregation area is overloaded according to the consumption data; When the target aggregation area is overloaded, the total power of all the new power loads is adjusted according to the centralized control system, and an adjustment signal is sent to the distributed control system of the smart grid; The distributed control system performs distributed regulation on the consumption of the new type of power load according to the received regulation signal and the resource clustering demand strategy.

[0011] Another embodiment of the present invention provides a flexible resource aggregation and control system for a smart grid, including: The power load spatial feature analysis module is used to analyze the acquired operating status data of the new power load in the target area to obtain the spatial distribution characteristics of the new power load in the operating state; An aggregation model building module, used to determine a candidate aggregation area according to the spatial distribution characteristics, obtain power communication infrastructure data of the candidate aggregation area, and build a target aggregation area screening model according to the power communication infrastructure data; An aggregation model processing module, used to process the target aggregation area screening model to determine the target aggregation area; A strategy formulation module, configured to convert the corresponding new power load in the target aggregation area into an equivalent impedance, and determine a resource clustering demand strategy for the target aggregation area based on the equivalent impedance; The collaborative control module is used to collaboratively control the operating parameters of the corresponding new power loads in the target aggregation area to match the resource clustering demand strategy.

[0012] Furthermore, the operating status data includes real-time power data, real-time load data and historical operating data of the new power load, and the power load spatial feature analysis module includes: A feature extraction unit, configured to extract features from the real-time power data to obtain a first distribution result reflecting the load density of the new power load; A comparison unit, used for comparing the real-time load data with a preset load threshold to obtain a second distribution result reflecting the load density of the new power load; A prediction and analysis unit, configured to perform artificial intelligence prediction on the historical operation data to obtain a third distribution result reflecting the load density of the new power load; An integration unit is used to integrate and analyze the first distribution result, the second distribution result and the third distribution result to obtain the spatial distribution characteristics of the new power load in the operating state.

[0013] Furthermore, the aggregation model building module includes: an aggregation unit, configured to use the acquired position in the first load area and the position of the selected power transmission node as candidate aggregation points according to the distribution of the new power load in the spatial distribution feature, and construct the candidate aggregation area with the candidate aggregation points; A power communication infrastructure analysis unit, configured to analyze the acquired power infrastructure data and communication infrastructure data within the candidate aggregation area to obtain the power communication infrastructure data; The aggregation area screening model construction unit is used to construct the target aggregation area screening model according to the power communication infrastructure data and the spatial distribution characteristics, and the target aggregation area screening model is represented by the following formula: in, It is Node to The distance between the aggregation nodes, Is the control system to the The distance between the aggregation nodes, It describes A binary decision variable for whether there is a clustering point among the nodes. is the total number of nodes in a given feeder, and They are respectively The running and installation costs associated with the aggregation point for each node, is a factor of constitute.

[0014] Furthermore, the strategy formulation module includes: A clustering unit, configured to obtain power consumption data of the new power loads in the target aggregation area within a selected time period, construct a clustering data set based on the power consumption data, and divide the clustering data set into a plurality of clusters; The impedance conversion unit is used to calculate the distance between each cluster according to a preset distance calculation formula, and convert the new type of power load into a corresponding impedance according to the calculation result.

[0015] Furthermore, the collaborative control module includes: an overload judgment unit, configured to monitor the voltage and power consumption data of each new type of power load in the target aggregation area through a centralized control system of the smart grid, and judge whether the target aggregation area is overloaded according to the consumption data; A centralized regulating unit, used for regulating the total power of all the new power loads according to the centralized control system when the target aggregation area is overloaded, and sending a regulating signal to the distributed control system of the smart grid; A distributed regulation unit is used for the distributed control system to perform distributed regulation on the consumption of the new type of power load according to the received regulation signal and the resource clustering demand strategy.

[0016] Compared with the prior art, the embodiments of the present invention have the following advantages: (1) By considering the spatial distribution of new power loads and the aggregation cost to construct the optimal aggregation area, the aggregation area and strategic points can be accurately determined to optimize resource allocation, thereby reducing the differences in power load demand in different regions and avoiding oversupply or undersupply of power in local areas, thereby improving the stability of the entire power system. (2) The coordinated work of the distributed control system and the centralized control system can achieve more effective resource deployment and coordination, thereby improving the control efficiency of the power grid operation and the stability of the power system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a method for aggregating and controlling flexibility resources of a smart grid in one embodiment of the present invention; Figure 2It is a structural block diagram of a flexible resource aggregation and control system of a smart grid in one embodiment of the present invention; Figure 3 It is a structural block diagram of a power load spatial characteristic analysis module of a flexible resource aggregation and control system of a smart grid in one embodiment of the present invention; Figure 4 It is a structural block diagram of an aggregation model building module of a flexibility resource aggregation and control system of a smart grid in one embodiment of the present invention; Figure 5 It is a structural block diagram of a strategy formulation module of a flexible resource aggregation and control system of a smart grid in one embodiment of the present invention; Figure 6 It is a structural block diagram of a collaborative control module of a flexible resource aggregation and control system of a smart grid in one embodiment of the present invention; Figure 7 It is a structural schematic diagram of one embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0020] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0021] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0022] New power loads are characterized by diversification, intelligence, and high efficiency. They include not only traditional industrial, commercial, and residential power equipment, but also new power equipment and systems such as electric vehicles, energy storage systems, and distributed energy. These new power loads have higher requirements for power quality, power supply reliability, and flexibility.

[0023] In view of the above requirements, an embodiment of the present invention provides a method. For details, see Figure 1 , Figure 1 The figure shows a flow chart of a method for aggregating and controlling flexibility resources of a smart grid in one embodiment of the present invention, which includes the following steps: S1. Analyze the acquired operating status data of the new type of power load in the target area to obtain the spatial distribution characteristics of the new type of power load in the operating state.

[0024] Understandably, smart grids need to handle widely distributed users whose power load demands vary significantly in space. Power demands vary in different regions and time periods. Therefore, smart grids need to accurately determine aggregation areas to optimize resource allocation. This involves in-depth analysis of the spatial distribution of users and considering how to reasonably divide areas to balance power loads.

[0025] When collecting the operating data of new power loads in various regions, these data usually cover multiple aspects to fully reflect the operating status of new power loads and the power consumption of users. Specifically, the operating status data of new power loads mainly includes the following aspects: real-time power data, real-time load data and historical operating data of new power loads, specifically: In this embodiment, feature extraction is performed on the real-time power data to obtain a first distribution result reflecting the load density of the new power load.

[0026] Real-time power data and real-time load data provide the power consumption and load status of new power loads at a specific moment. These data can directly reflect the real-time operating status of the power load.

[0027] First, the power data needs to be cleaned and formatted, such as removing outliers and processing missing data. It is understandable that since the power is related to the geographical location and time of the new power load, that is, the load will be high or low in different time periods and different regions, the power data can effectively reflect the spatial distribution characteristics of the new power load.

[0028] Preferably, the means that can be used to extract features from the real-time electricity data include but are not limited to: statistical feature extraction, time series feature extraction, spectrum feature extraction, etc.

[0029] After extracting data features of the real-time electric quantity, the load density of the new electric load is obtained, that is, the first distribution result refers to the distribution result of whether the load density of the new electric load is high or low or other.

[0030] In this embodiment, the real-time load data is compared with a preset load threshold to obtain a second distribution result reflecting the load density of the new power load.

[0031] In this embodiment, the acquired real-time load data values ​​may be arranged in chronological order, based on which a fixed value load is selected as a preset load threshold, which represents an important limit of the electric load based on the load.

[0032] For each real-time load data point, we compare it with the preset load threshold: If the real-time load data point is greater than the preset load threshold, the load at that time point is considered to be "high density" (or "high load"); If the real-time load data point is less than the preset load threshold, the load at that time point is considered to be "low density" (or "low load").

[0033] Based on the comparison results, a second distribution result reflecting the new type of power load density can be generated, that is, the second distribution result refers to a distribution result of load density displayed by visualization tools such as line charts, bar charts and heat maps, or a sequence with the same length as the original real-time load data, but each element is marked as "high density" or "low density" (for example, 1 represents "high density" and 0 represents "low density").

[0034] In this step, artificial intelligence prediction is performed on the historical operation data to obtain a third distribution result reflecting the load density of the new power load.

[0035] It is understandable that in some embodiments, after preprocessing the historical operation data, a suitable artificial intelligence prediction model is selected according to the characteristics of the data. The optional artificial intelligence prediction models include but are not limited to: time series prediction model, random forest, gradient boosting tree (GBDT) and deep learning model, etc.

[0036] The historical data set can then be divided into training set, validation set and test set and input into the artificial intelligence model for model training, validation and evaluation. Based on the prediction results, a third distribution result is generated, that is, the load density distribution of the new power load based on the historical operation data. This can be a time series label sequence, statistical indicators or visualization chart.

[0037] Furthermore, the obtained load density distribution results need to be integrated and analyzed to reveal the spatial distribution characteristics of the new power loads. Specifically: The first distribution result, the second distribution result and the third distribution result are integrated and analyzed to obtain the spatial distribution characteristics of the new power load in the operating state.

[0038] In some embodiments, based on the above three distribution results, spatial analysis techniques (such as spatial clustering, spatial autocorrelation analysis, etc.) can be used to identify the spatial aggregation pattern or partition of power loads, or the analysis results can be integrated based on time distribution to further analyze the spatial variation of load density in different time periods. This can clearly and intuitively show which areas have higher / lower load density in a specific time period.

[0039] S2-S3, determining a candidate aggregation area according to the spatial distribution characteristics, obtaining power communication infrastructure data of the candidate aggregation area, and constructing a target aggregation area screening model according to the power communication infrastructure data.

[0040] Based on the spatial distribution characteristics of the power load, suitable candidate aggregation areas are screened out. Since the present invention aims to find the best aggregation area, it can efficiently aggregate the power load in the area and achieve optimal configuration and efficient utilization of power resources through intelligent scheduling and management. Therefore, according to the distribution of power load, locations in high-load areas or key nodes of power transmission can be selected as candidate aggregation points.

[0041] In this embodiment, according to the distribution of the new type of power load in the spatial distribution characteristics, the acquired position in the first load area and the position of the selected node for power transmission are used as candidate aggregation points, and the candidate aggregation area is constructed with the candidate aggregation points. In this embodiment, the first load area refers to an area where the power load spatial distribution characteristics are the optimal load density distribution. The power load in the first load area is evenly distributed, and there will be no overload or underload, thereby ensuring the stable operation and power supply quality of the power grid.

[0042] It can be understood that the aggregation area is usually located in an area with concentrated power load, convenient transportation and rich resources, which is convenient for the transmission and distribution of electricity. Therefore, in this embodiment, after the candidate aggregation area is obtained, it is necessary to analyze the power infrastructure data and communication infrastructure data within the candidate aggregation area to obtain the power communication infrastructure data.

[0043] Preferably, in this embodiment, the power infrastructure conditions of the candidate aggregation area are evaluated, including grid access capability, power transmission capacity, etc., and the communication infrastructure conditions of the candidate aggregation area are considered to ensure smooth communication with the smart grid control center and other aggregation points.

[0044] Furthermore, in this embodiment, the target aggregation area screening model is constructed according to the power communication infrastructure data and the spatial distribution characteristics, and the target aggregation area screening model is represented by the following formula: in, It is Node to The distance between the aggregation nodes, Is the control system to the The distance between the aggregation nodes, It describes A binary decision variable for whether there is a clustering point among the nodes. is the total number of nodes in a given feeder, and They are respectively The running and installation costs associated with the aggregation point for each node, is a factor of constitute.

[0045] Specifically, It can be expressed by the following formula: If from Node to If any node on the path of nodes has a cluster point, then becomes zero, making , The product of is zero.

[0046] In particular, from Aggregation nodes to The distance between nodes It can be written in matrix form as follows: and , that is, from the central aggregation node to the The distance between nodes can be expressed as: in, It mainly depends on the network topology and the spatial distribution of consumers.

[0047] Since the target aggregation area screening model contains different units (for example, the first part is the distance, while the second part is the cost associated with the electricity communication infrastructure), it is standardized as follows: in, and They correspond to the first and second parts of the formula target aggregation area screening model, respectively. and are the weights assigned to the first and second parts of the formula target aggregate area screening model, respectively.

[0048] also, is used to standardize the first part (i.e. ) distance, and For standardization of the second part (i.e. ), in particular, is the maximum distance that can occur in a given system, which occurs when there is no aggregation and each new type of power load is reached directly by the central aggregator, so this can be achieved by The sum is simply obtained.

[0049] Similarly, is the maximum number of possible aggregation points in the network, which occurs when every node is an aggregation point, so will be equal to the total number of nodes in the given network. The constraints are expressed as follows: in, is the maximum possible distance from the consumer to the aggregation point. The number of aggregation points is limited.

[0050] It can be understood that the target aggregation area screening model constructed based on the spatial distribution of power load and the power and communication infrastructure conditions in the region can reflect the uniform distribution and stable operation of the power load in the optimal aggregation area. Furthermore, the target aggregation area screening model is processed to determine the target aggregation area. The target aggregation area is the selected optimal aggregation area. The construction and operation costs of the optimal aggregation area are relatively low, and it can bring significant economic benefits, such as reducing grid losses and improving power supply efficiency. In addition, the power facilities in the optimal aggregation area are reasonably laid out, with complete safety measures and emergency response mechanisms, which can ensure the safe and stable operation of the power grid.

[0051] It is worth noting that users or facilities in the region have high similarity in electricity consumption characteristics, such as similar peak hours, similar electricity load curves, etc. This helps to formulate more accurate power dispatching and management strategies and improve the operating efficiency of the power system.

[0052] S4. Convert the corresponding new power load in the target aggregation area into an equivalent impedance, and determine the resource clustering demand strategy of the target aggregation area based on the equivalent impedance.

[0053] The purpose of calculating equivalent impedance is to optimize power transmission, support the formulation of aggregation strategies, improve system stability and support economic dispatch. Equivalent impedance reflects the loss of power during transmission. By calculating equivalent impedance, the efficiency of power transmission under different aggregation strategies can be evaluated.

[0054] After calculating the target aggregation area, the flexible resources in each area need to be aggregated to the corresponding strategic location. Since the aggregated load and equivalent impedance are both functions of time, in order to solve this situation, the power consumption of a given network is first clustered into a reasonable number of clusters. , and then use these clusters to calculate the equivalent impedance.

[0055] Specifically, in this embodiment, power consumption data of the new power loads in the target aggregation area within a selected time period is obtained, a clustering data set is constructed based on the power consumption data, and the clustering data set is divided into a number of clusters.

[0056] Preferably, a hierarchical clustering technique may be used to cluster the hourly time series power consumption data into a predefined number of clusters to reflect daily and seasonal load variations.

[0057] Furthermore, the distance between each cluster is calculated according to a preset distance calculation formula, and according to the calculation result, the new type of power load is converted into a corresponding impedance, specifically: Calculate the distances between all clustered data sets, assuming that each data set is an independent cluster, find the closest pair of clusters and merge them into one cluster, thereby reducing the number of clusters by one, calculate the distance between the new cluster and the remaining old clusters, and repeat the steps of merging and calculating the distance between the new cluster and the remaining old clusters until the clustered data set is clustered into a given number of clusters.

[0058] In this embodiment, a preset distance calculation formula is used to calculate the distance between clusters. Preferably, the fully connected distance method is also called the longest distance method or the fully connected method. It is a commonly used inter-class distance measurement method in hierarchical clustering algorithms. It defines the distance between categories by taking the maximum value of all possible observation pairs between two categories.

[0059] It can be understood that the preset distance calculation formula refers to the fully connected distance calculation formula. In fact, the distance between cluster pairs is basically the power demand difference between the two clusters. The preset distance calculation formula is used to calculate the cluster and The distance between them is expressed by the following formula: in, and Clusters and data.

[0060] After calculating the distances between clusters and realizing load clustering of power loads, the load of each node in the target aggregation area is converted into impedance. The conversion process is expressed by the following formula: in, is the load impedance, is power, It is The voltage at the connection point of a node.

[0061] In the embodiment of the present invention, by converting new types of power loads into corresponding equivalent impedances, clustering of time series data is essential to reflect the daily seasonal changes in loads. These changes are manifested as differences in power consumption, which are then reflected in the changes in the equivalent impedance of each aggregation area.

[0062] It can be understood that, according to the equivalent impedance of each area, an aggregation demand strategy for flexible resources in the target aggregation area is formulated. Specifically, in some embodiments, the formulation of the resource clustering demand strategy includes but is not limited to the following steps: First, the equivalent impedance is analyzed. By studying the changing trends and laws of the equivalent impedance, the differences in electrical characteristics of power networks in different regions can be understood.

[0063] Next, a scientific and reasonable resource aggregation demand strategy is formulated. According to the power consumption pattern and equivalent impedance, the power demand of new power loads in the target aggregation area in different time periods is determined. Based on this, a flexible resource scheduling and allocation strategy is formulated to ensure the stability and economy of power supply. In some implementations, advanced technologies such as energy storage systems and demand-side response can also be used to optimize the resource aggregation effect.

[0064] Finally, the formulated aggregation strategy can be implemented, and its effectiveness can be evaluated through real-time monitoring and data analysis, and adjusted and optimized as needed.

[0065] S5. Coordinated control of operating parameters of corresponding new power loads in the target aggregation area to match the resource clustering demand strategy.

[0066] It is understandable that the distribution system operator operates both the centralized control system and the distributed control system. The embodiment of the present invention aims to propose a hierarchical control architecture combining centralized and decentralized control to achieve more efficient deployment and coordination of aggregated resources. Specifically: In this embodiment, the centralized control system of the smart grid monitors the voltage and power consumption data of each new type of power load in the target aggregation area, and determines whether the target aggregation area is overloaded according to the consumption data.

[0067] In this embodiment, taking heat pumps and electric vehicles as new power loads, the centralized control system monitors the voltage and power consumption of all heat pumps and electric vehicles in the target aggregation area and measures the load of the power lines. In particular, the centralized control system calculates and defines the heat load of each line to identify whether there is an overloaded line.

[0068] Furthermore, when the target aggregation area is overloaded, the total power of all the new power loads is adjusted according to the centralized control system, and an adjustment signal is sent to the distributed control system of the smart grid.

[0069] When the load of any line in the target aggregation area exceeds the threshold, the centralized control system solves the overload problem by calculating and adjusting the total power of the new power load. Specifically, the power adjustment process is expressed by the following formula: in, and It is a parameter used to adjust the response of the centralized control system. and are the lower and upper limits of regulation, It is the heaviest line load in the low voltage distribution network. is the threshold set by the power distribution system, is the total power.

[0070] Through the above regulation process, the centralized control system will monitor each distributed control system and line, and send a control signal to each distributed control system when overload is identified. The centralized control system will adjust the power according to the availability of flexible loads in each distributed control system. Proportionately distributed to distributed control systems.

[0071] Furthermore, the distributed control system performs distributed regulation on the consumption of the new power load according to the received regulation signal and the resource clustering demand strategy.

[0072] When the distributed control system receives the regulation signal of voltage violation or overload of heat pumps and electric vehicles from the centralized control system in the target aggregation area, the distributed control system will adjust the power consumption of heat pumps and electric vehicles, specifically: in, and are the power consumption that needs to be adjusted from the heat pump and electric vehicle in the #th distributed control system, and are the power consumption of the heat pump and electric vehicle measured at the #th DCS aggregation level, respectively, and are the power regulation from the heat pump and electric vehicle of the #th distributed control system required to keep its voltage within specified limits, and It is the power regulation of the heat pumps and electric vehicles required from the #th distributed control system in response to requests from the centralized control system.

[0073] Furthermore, the power regulation of the heat pump and electric vehicle in each distributed control system is expressed by the following formula: in, and is the parameter that regulates the local voltage controller that affects the heat pump consumption, and are the parameters of the local voltage controller for electric vehicles, / is the voltage at the connection point of the heat pump / electric vehicle, / is the threshold value specified by the power distribution system, / and / are the minimum and maximum power limits for heat pumps / electric vehicles within the corresponding aggregation area.

[0074] The centralized control system will adjust the power The distribution is proportionally distributed to the distributed control systems. Specifically, the distribution between the distributed control systems is based on the instantaneous consumption of the heat pump / electric vehicle and the resource clustering demand strategy. The distribution process is expressed by the following formula: in, is the total number of aggregation areas.

[0075] In summary, the embodiment of the present invention analyzes the operating status of the new power load in the target area to obtain the spatial distribution characteristics of the new power load in the operating state, and further determines the aggregation area according to the spatial distribution characteristics of the new power load, and based on the power communication infrastructure conditions of the candidate aggregation area, it can more accurately determine the optimal aggregation area; the embodiment of the present invention constructs an equivalent aggregation network by converting the power load into an equivalent impedance to formulate a resource clustering demand strategy and flexibly configure resources; finally, by collaboratively controlling the distributed control system and the centralized control system of the power load in the aggregation area, the time and computing burden of the power grid solution are reduced, and the control efficiency of the power grid operation is improved.

[0076] An embodiment of the present invention provides a flexible resource aggregation and control system for a smart grid. For details, see Figure 2 , Figure 2 The figure shows a block diagram of a flexible resource aggregation and control system of a smart grid in one embodiment of the present invention, which specifically includes: The power load spatial feature analysis module M1 is used to analyze the acquired operating status data of the new power load in the target area to obtain the spatial distribution characteristics of the new power load in the operating state; the aggregation model construction module M2 is used to determine the candidate aggregation area according to the spatial distribution characteristics, and obtain the power communication infrastructure data of the candidate aggregation area, and construct the target aggregation area screening model according to the power communication infrastructure data; the aggregation model processing module M3 is used to process the target aggregation area screening model to determine the target aggregation area; the strategy formulation module M4 is used to convert the corresponding new power load in the target aggregation area into an equivalent impedance, and determine the resource clustering demand strategy of the target aggregation area based on the equivalent impedance; the collaborative control module M5 is used to collaboratively control the operating parameters of the corresponding new power load in the target aggregation area to match the resource clustering demand strategy.

[0077] In this embodiment, the operating status data includes real-time power data, real-time load data and historical operating data of the new power load.

[0078] As an example, the real-time power data, real-time load data and historical operation data of the new power load are analyzed by the power load spatial feature analysis module M1. For details, please refer to Figure 3 , Figure 3 It is a structural block diagram of the power load spatial feature analysis module of the flexible resource aggregation and control system of the smart grid in one embodiment of the present invention, including a feature extraction unit M11, a comparison unit M12, a prediction analysis unit M13 and an integration unit M14.

[0079] Specifically, the real-time power data is feature extracted through the feature extraction unit M11 to obtain a first distribution result reflecting the load density of the new power load. The real-time power data and real-time load data provide the power consumption and load status of the new power load at a specific moment. These data can directly reflect the immediate operating status of the power load.

[0080] First, the power data needs to be cleaned and formatted, such as removing outliers and processing missing data. It is understandable that since the power is related to the geographical location and time of the new power load, that is, the load will be high or low in different time periods and different regions, the power data can effectively reflect the spatial distribution characteristics of the new power load.

[0081] Preferably, the means that can be used to extract features from the real-time electricity data include but are not limited to: statistical feature extraction, time series feature extraction, spectrum feature extraction, etc.

[0082] After extracting data features of the real-time electric quantity, the load density of the new electric load is obtained, that is, the first distribution result refers to the distribution result of whether the load density of the new electric load is high or low or other.

[0083] The real-time load data is compared with the preset load threshold by the comparison unit M12 to obtain a second distribution result reflecting the load density of the new power load. The acquired real-time load data values ​​can be arranged in chronological order, based on which a fixed value load is selected as the preset load threshold, which represents a certain important limit of the power load based on the load.

[0084] For each real-time load data point, compare it with the preset load threshold: If the real-time load data point is greater than the preset load threshold, the load at that time point is considered to be "high density" (or "high load"); If the real-time load data point is less than the preset load threshold, the load at that time point is considered to be "low density" (or "low load").

[0085] Based on the comparison results, a second distribution result reflecting the new type of power load density can be generated, that is, the second distribution result refers to a distribution result of load density displayed by visualization tools such as line charts, bar charts and heat maps, or a sequence with the same length as the original real-time load data, but each element is marked as "high density" or "low density" (for example, 1 represents "high density" and 0 represents "low density").

[0086] Through the prediction and analysis unit M13, the historical operation data is predicted by artificial intelligence to obtain a third distribution result reflecting the load density of the new power load. After preprocessing the historical operation data, a suitable artificial intelligence prediction model is selected according to the characteristics of the data. The optional artificial intelligence prediction models include but are not limited to: time series prediction model, random forest, gradient boosting tree (GBDT) and deep learning model.

[0087] The historical data set can then be divided into training set, validation set and test set and input into the artificial intelligence model for model training, validation and evaluation. Based on the prediction results, a third distribution result is generated, that is, the load density distribution of the new power load based on the historical operation data. This can be a time series label sequence, statistical indicators or visualization chart.

[0088] The first distribution result, the second distribution result and the third distribution result are integrated and analyzed by the integration unit M14 to obtain the spatial distribution characteristics of the new power load in the operating state.

[0089] Based on the above three distribution results, spatial analysis techniques (such as spatial clustering, spatial autocorrelation analysis, etc.) can be used to identify the spatial aggregation pattern or partition of power load, or to integrate the analysis results based on time distribution to further analyze the spatial changes of load density in different time periods. This can clearly and intuitively show which areas have higher / lower load density in a specific time period.

[0090] In this embodiment, through the aggregation model construction module M2, based on the spatial distribution characteristics of the power load, a suitable candidate aggregation area is screened out. Since the present invention is intended to find the best aggregation area, it can efficiently aggregate the power load in the area and achieve optimal configuration and efficient utilization of power resources through intelligent scheduling and management. Therefore, according to the distribution of power load, a location in a high-load area or a key node of power transmission can be selected as a candidate aggregation point. The aggregation model construction module M2 includes an aggregation unit M21, a power communication infrastructure analysis unit M22, and an aggregation area screening model construction unit M23. Please refer to Figure 4 , Figure 4 This is a block diagram of the aggregation model building module of the flexibility resource aggregation and control system of the smart grid in one embodiment of the present invention, wherein: Through the aggregation unit M21, according to the distribution of the new type of power load in the spatial distribution characteristics, the acquired position in the first load area and the position of the selected node of power transmission are used as candidate aggregation points, and the candidate aggregation area is constructed with the candidate aggregation points. The first load area refers to the area where the power load spatial distribution characteristics are the optimal load density distribution. The power load in the first load area is evenly distributed, and there will be no overload or underload, thereby ensuring the stable operation of the power grid and the power supply quality.

[0091] It can be understood that the aggregation area is usually located in an area with concentrated power load, convenient transportation and rich resources, which is convenient for the transmission and distribution of electricity. Therefore, in this embodiment, after the candidate aggregation area is obtained, it is necessary to use the power communication infrastructure analysis unit M22 to analyze the power infrastructure data and communication infrastructure data in the candidate aggregation area to obtain the power communication infrastructure data.

[0092] Preferably, the power infrastructure conditions of the candidate aggregation areas are evaluated, including grid access capabilities, power transmission capacity, etc., and the communication infrastructure conditions of the candidate aggregation areas are considered to ensure smooth communication with the smart grid control center and other aggregation points.

[0093] The target aggregation area screening model is constructed by the aggregation area screening model construction unit M23 according to the power communication infrastructure data and the spatial distribution characteristics. The target aggregation area screening model is represented by the following formula: in, It is Node to The distance between the aggregation nodes, Is the control system to the The distance between the aggregation nodes, It describes A binary decision variable for whether there is a clustering point among the nodes. is the total number of nodes in a given feeder, and They are respectively The running and installation costs associated with the aggregation point for each node, is a factor of constitute.

[0094] Specifically, It can be expressed by the following formula: If from Node to If any node on the path of nodes has a cluster point, then becomes zero, making , The product of is zero.

[0095] In particular, from Aggregation nodes to The distance between nodes It can be written in matrix form as follows: and , that is, from the central aggregation node to the The distance between nodes can be expressed as: in, It mainly depends on the network topology and the spatial distribution of consumers.

[0096] Since the target aggregation area screening model contains different units (for example, the first part is the distance, while the second part is the cost associated with the electricity communication infrastructure), it is standardized as follows: in, and They correspond to the first and second parts of the formula target aggregation area screening model, respectively. and are the weights assigned to the first and second parts of the formula target aggregate area screening model, respectively.

[0097] also, is used to standardize the first part (i.e. ) distance, and For standardization of the second part (i.e. ), in particular, is the maximum distance that can occur in a given system, which occurs when there is no aggregation and each new type of power load is reached directly by the central aggregator, so this can be achieved by The sum is simply obtained.

[0098] Similarly, is the maximum number of possible aggregation points in the network, which occurs when every node is an aggregation point, so will be equal to the total number of nodes in the given network. The constraints are expressed as follows: in, is the maximum possible distance from the consumer to the aggregation point. The number of aggregation points is limited.

[0099] It can be understood that the target aggregation area screening model constructed based on the spatial distribution of power load and the power and communication infrastructure conditions in the region can reflect the uniform distribution and stable operation of power load in the optimal aggregation area.

[0100] Furthermore, the target aggregation area screening model is processed by the aggregation model processing module M3 to determine the target aggregation area, which is the selected optimal aggregation area. The construction and operation costs of the optimal aggregation area are relatively low, and it can bring significant economic benefits, such as reducing grid losses and improving power supply efficiency. In addition, the layout of power facilities in the optimal aggregation area is reasonable, and it has complete safety measures and emergency response mechanisms, which can ensure the safe and stable operation of the power grid. For details, please refer to Figure 5 , Figure 5 It is a structural block diagram of a strategy formulation module of a flexibility resource aggregation and control system of a smart grid in one embodiment of the present invention.

[0101] In this embodiment, the strategy formulation module M4 includes: a clustering unit M41 and an impedance conversion unit M42. Specifically, The power consumption data of the new power load in the target aggregation area in the selected time period is obtained through the clustering unit M41, and a clustering data set is constructed based on the power consumption data; the clustering data set is divided into a number of clusters. Preferably, a hierarchical clustering technique can be used to cluster the hourly time series power consumption data into a predefined number of clusters to reflect daily and seasonal load changes.

[0102] The impedance conversion unit M42 calculates the distance between each cluster according to a preset distance calculation formula, and converts the new type of power load into a corresponding impedance according to the calculation result. Calculate the distances between all clustered data sets, assuming that each data set is an independent cluster, find the closest pair of clusters and merge them into one cluster, thereby reducing the number of clusters by one, calculate the distance between the new cluster and the remaining old clusters, and repeat the steps of merging and calculating the distance between the new cluster and the remaining old clusters until the clustered data set is clustered into a given number of clusters.

[0103] The distance between clusters is calculated using the preset distance calculation formula. The preset distance calculation formula refers to the fully connected distance method. The distance between cluster pairs is basically the power demand difference between the two clusters. The preset distance calculation formula is used to calculate the cluster and The distance between them is expressed by the following formula: in, and Clusters and data.

[0104] After calculating the distances between clusters and realizing load clustering of power loads, the load of each node in the target aggregation area is converted into impedance. The conversion process is expressed by the following formula: in, is the load impedance, is power, It is The voltage at the connection point of a node.

[0105] The purpose of calculating equivalent impedance is to optimize power transmission, support the formulation of aggregation strategies, improve system stability and support economic dispatch. Equivalent impedance reflects the loss of power during transmission. By calculating equivalent impedance, the efficiency of power transmission under different aggregation strategies can be evaluated. After calculating the target aggregation area, the flexible resources in each area need to be aggregated to the corresponding strategic location. Since both the aggregated load and the equivalent impedance are functions of time, in order to solve this situation, the power consumption of a given network is first clustered into a reasonable number of clusters, and then these clusters are used to calculate the equivalent impedance.

[0106] In this embodiment, the coordinated control module M5 is used to perform coordinated control combining centralized control and distributed control on the operating parameters of the corresponding new power loads in the target aggregation area. For details, please refer to Figure 6 , Figure 6 It is a block diagram of the coordinated control module structure of the flexible resource aggregation and control system of the smart grid in one embodiment of the present invention, including: an overload judgment unit M51, a centralized adjustment unit M52 and a distributed adjustment unit M53, wherein: The overload judgment unit M51 monitors the voltage and power consumption data of each new type of power load in the target aggregation area through the centralized control system of the smart grid, and judges whether the target aggregation area is overloaded according to the consumption data.

[0107] Preferably, taking heat pumps and electric vehicles as new power loads, the centralized control system monitors the voltage and power consumption of all heat pumps and electric vehicles in the target aggregation area and measures the load of the power lines. In particular, the centralized control system identifies whether there is an overloaded line by calculating and defining the heat load of each line.

[0108] The centralized regulating unit M52 regulates the total power of all the new power loads according to the centralized control system when the target aggregation area is overloaded, and sends a regulating signal to the distributed control system of the smart grid.

[0109] In a preferred embodiment, when the load of any line in the target aggregation area exceeds the threshold, the centralized control system solves the overload problem by calculating and adjusting the total power of the new power load. Specifically, the power adjustment process is represented by the following formula: in, and It is a parameter used to adjust the response of the centralized control system. and are the lower and upper limits of regulation, It is the heaviest line load in the low voltage distribution network. is the threshold set by the power distribution system, is the total power.

[0110] Through the above regulation process, the centralized control system will monitor each distributed control system and line, and send a control signal to each distributed control system when an overload is identified. The centralized control system will adjust the power according to the availability of flexible loads in each distributed control system. Proportionately distributed to distributed control systems.

[0111] The distributed regulation unit M53, the distributed control system performs distributed regulation on the consumption of the new power load according to the received regulation signal and the resource clustering demand strategy.

[0112] In a preferred embodiment, when the distributed control system receives a regulation signal of voltage violation or overload of the heat pump and the electric vehicle from the centralized control system in the target aggregation area, the distributed control system will adjust the power consumption of the heat pump and the electric vehicle, specifically: in, and are the power consumption that needs to be adjusted from the heat pump and electric vehicle in the #th distributed control system, and are the power consumption of the heat pump and electric vehicle measured at the #th DCS aggregation level, respectively, and are the power regulation from the heat pump and electric vehicle of the #th distributed control system required to keep its voltage within specified limits, and It is the power regulation of the heat pumps and electric vehicles required from the #th distributed control system in response to requests from the centralized control system.

[0113] Furthermore, the power regulation of the heat pump and electric vehicle in each distributed control system is expressed by the following formula: in, and is the parameter that regulates the local voltage controller that affects the heat pump consumption, and are the parameters of the local voltage controller for electric vehicles, / is the voltage at the connection point of the heat pump / electric vehicle, / is the threshold value specified by the power distribution system, / and / are the minimum and maximum power limits for heat pumps / electric vehicles within the corresponding aggregation area.

[0114] The centralized control system will adjust the power The distribution is proportionally distributed to the distributed control systems. Specifically, the distribution between the distributed control systems is based on the instantaneous consumption of the heat pump / electric vehicle and the resource clustering demand strategy. The distribution process is expressed by the following formula: in, is the total number of aggregation areas.

[0115] like Figure 7 As shown, the embodiment of the present invention further provides a computer device, Figure 7 A structural block diagram of a preferred embodiment of a computer device provided by the present invention, wherein the computer device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the flexibility resource aggregation and control method of the smart grid as described above when executing the computer program.

[0116] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0117] The processor may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may be any conventional processor. The processor is the control center of the terminal device, and various parts of the terminal device are connected using various interfaces and lines.

[0118] The memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory can also be other volatile solid-state storage devices.

[0119] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 7 The structural block diagram is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium may be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0120] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to perform the steps in the method for aggregating and controlling flexibility resources of a smart grid in the above embodiment, for example Figure 1 Steps S1 to S5 described in .

[0121] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for aggregating and controlling flexibility resources of a smart grid, characterized in that: include: Analyze the acquired operating status data of the new type of power load in the target area to obtain the spatial distribution characteristics of the new type of power load in the operating state; Determine a candidate aggregation area according to the spatial distribution characteristics, obtain power communication infrastructure data of the candidate aggregation area, and construct a target aggregation area screening model according to the power communication infrastructure data; Processing the target aggregation region screening model to determine the target aggregation region; Converting the corresponding new power load in the target aggregation area into an equivalent impedance, and determining the resource clustering demand strategy of the target aggregation area based on the equivalent impedance; The operating parameters of the corresponding new power loads in the target aggregation area are collaboratively controlled to match the resource clustering demand strategy.

2. The method for aggregating and controlling flexibility resources of a smart grid according to claim 1, characterized in that: The operation status data includes real-time power data, real-time load data and historical operation data of the new power load; The acquired operating status data of the new type of electric load in the target area is analyzed to obtain the spatial distribution characteristics of the new type of electric load in the operating state, including: Extracting features from the real-time power data to obtain a first distribution result reflecting the load density of the new power load; Comparing the real-time load data with a preset load threshold to obtain a second distribution result reflecting the load density of the new power load; Performing artificial intelligence prediction on the historical operation data to obtain a third distribution result reflecting the load density of the new power load; The first distribution result, the second distribution result and the third distribution result are integrated and analyzed to obtain the spatial distribution characteristics of the new power load in the operating state.

3. The method for aggregating and controlling flexibility resources of a smart grid according to claim 1, characterized in that: The determining of the candidate aggregation area according to the spatial distribution characteristics, acquiring the power communication infrastructure data of the candidate aggregation area, and constructing the target aggregation area screening model according to the power communication infrastructure data includes: According to the distribution of the new type of power load in the spatial distribution feature, the acquired position in the first load area and the position of the selected power transmission node are used as candidate aggregation points, and the candidate aggregation area is constructed with the candidate aggregation points; Analyze the acquired power infrastructure data and communication infrastructure data within the candidate aggregation area to obtain the power communication infrastructure data; The target aggregation area screening model is constructed according to the power communication infrastructure data and the spatial distribution characteristics. The target aggregation area screening model is expressed by the following formula: in, It is Node to The distance between the aggregation nodes, Is the control system to the The distance between the aggregation nodes, It describes A binary decision variable for whether there is a clustering point among the nodes. is the total number of nodes in a given feeder, and They are respectively The running and installation costs associated with the aggregation point for each node, is a factor of constitute.

4. The method for aggregating and controlling flexibility resources of a smart grid according to claim 1, characterized in that: The converting the corresponding new type of power load in the target aggregation area into an equivalent impedance comprises: Acquire power consumption data of new power loads in the target aggregation area within a selected time period, and construct a clustering data set based on the power consumption data; Dividing the clustering data set into a number of clusters; The distances between the clusters are calculated according to a preset distance calculation formula, and the new type of power load is converted into a corresponding impedance according to the calculation result.

5. The method for aggregating and controlling flexibility resources of a smart grid according to claim 1, characterized in that: The collaborative control of the operating parameters of the corresponding new power loads in the target aggregation area includes: Monitoring the voltage and power consumption data of each new type of power load in the target aggregation area through a centralized control system of the smart grid, and determining whether the target aggregation area is overloaded according to the consumption data; When the target aggregation area is overloaded, the total power of all the new power loads is adjusted according to the centralized control system, and an adjustment signal is sent to the distributed control system of the smart grid; The distributed control system performs distributed regulation on the consumption of the new type of power load according to the received regulation signal and the resource clustering demand strategy.

6. A flexible resource aggregation and control system for a smart grid, characterized in that: include: The power load spatial feature analysis module is used to analyze the acquired operating status data of the new power load in the target area to obtain the spatial distribution characteristics of the new power load in the operating state; An aggregation model building module, used to determine a candidate aggregation area according to the spatial distribution characteristics, obtain power communication infrastructure data of the candidate aggregation area, and build a target aggregation area screening model according to the power communication infrastructure data; An aggregation model processing module, used to process the target aggregation area screening model to determine the target aggregation area; A strategy formulation module, configured to convert the corresponding new power load in the target aggregation area into an equivalent impedance, and determine a resource clustering demand strategy for the target aggregation area based on the equivalent impedance; The collaborative control module is used to collaboratively control the operating parameters of the corresponding new power loads in the target aggregation area to match the resource clustering demand strategy.

7. The flexibility resource aggregation and control system of the smart grid as claimed in claim 6, characterized in that: The operation status data includes real-time power data, real-time load data and historical operation data of the new power load, and the power load spatial feature analysis module includes: A feature extraction unit, configured to extract features from the real-time power data to obtain a first distribution result reflecting the load density of the new power load; A comparison unit, used for comparing the real-time load data with a preset load threshold to obtain a second distribution result reflecting the load density of the new power load; A prediction and analysis unit, configured to perform artificial intelligence prediction on the historical operation data to obtain a third distribution result reflecting the load density of the new power load; An integration unit is used to integrate and analyze the first distribution result, the second distribution result and the third distribution result to obtain the spatial distribution characteristics of the new power load in the operating state.

8. The flexibility resource aggregation and control system of the smart grid as claimed in claim 6, characterized in that: The aggregation model building module includes: an aggregation unit, configured to use the acquired position in the first load area and the position of the selected power transmission node as candidate aggregation points according to the distribution of the new power load in the spatial distribution feature, and construct the candidate aggregation area with the candidate aggregation points; A power communication infrastructure analysis unit, configured to analyze the acquired power infrastructure data and communication infrastructure data within the candidate aggregation area to obtain the power communication infrastructure data; The aggregation area screening model construction unit is used to construct the target aggregation area screening model according to the power communication infrastructure data and the spatial distribution characteristics, and the target aggregation area screening model is represented by the following formula: in, It is Node to The distance between the aggregation nodes, Is the control system to the The distance between the aggregation nodes, It describes A binary decision variable for whether there is a clustering point among the nodes. is the total number of nodes in a given feeder, and They are respectively The running and installation costs associated with the aggregation point for each node, is a factor of constitute.

9. The smart grid flexibility resource aggregation and control system according to claim 6, characterized in that: The strategy formulation module includes: A clustering unit, configured to obtain power consumption data of the new power loads in the target aggregation area within a selected time period, construct a clustering data set based on the power consumption data, and divide the clustering data set into a plurality of clusters; The impedance conversion unit is used to calculate the distance between each cluster according to a preset distance calculation formula, and convert the new type of power load into a corresponding impedance according to the calculation result.

10. The smart grid flexibility resource aggregation and control system according to claim 6, characterized in that: The collaborative control module includes: An overload judgment unit, configured to monitor the voltage and power consumption data of each new type of power load in the target aggregation area through a centralized control system of the smart grid, and judge whether the target aggregation area is overloaded according to the consumption data; A centralized regulating unit, configured to regulate the total power of all the new power loads according to the centralized control system when an overload occurs in the target aggregation area, and send a regulating signal to the distributed control system of the smart grid; A distributed regulation unit is used for the distributed control system to perform distributed regulation on the consumption of the new type of power load according to the received regulation signal and the resource clustering demand strategy.

Images