Power distribution network area charging pile bearing capacity dynamic evaluation and intelligent planning system and method

Abstract

The application discloses a power distribution network area charging pile bearing capacity dynamic evaluation and intelligent planning system and method, and the application can comprehensively identify the power quality and safety risk after the charging pile is connected by constructing a linkage verification mechanism covering multi-dimensional constraints such as voltage deviation, harmonic current and reverse load rate. Meanwhile, the application dynamically updates the remaining accessible load of each node by means of load prediction and real-time data, and outputs hierarchical access suggestions, realizes the upgrading from extensive estimation of the area to accurate control at the node level, and effectively optimizes the spatial layout of the charging pile. At the same time, the system generates a targeted optimization and improvement scheme based on the foregoing data and automatically calls a large model, so that the response cycle can be greatly shortened, thereby adapting to the large-scale rapid access demand of the charging pile. In addition, the application fully utilizes historical data for dynamic load prediction, so that the evaluation result has time variation and foresight, and can better cope with random fluctuations of charging load and multi-element application scenarios.

Description

Technical Field

[0001] This invention belongs to the field of power distribution network operation and management and charging pile access planning technology, specifically involving a dynamic assessment and intelligent planning system and method for the carrying capacity of charging piles in power distribution network areas. Background Technology

[0002] With the rapid development of the new energy vehicle industry, the large-scale connection of charging piles to power distribution networks has become an inevitable trend. Since 2024, relevant departments have successively issued policies that clearly require strengthening the management of power quality issues during the charging pile connection process to ensure the safe and stable operation of the power distribution network. Currently, the existing methods for assessing and planning the carrying capacity of charging piles in power distribution networks have many industry pain points and can no longer meet the actual application needs. Specifically, these include: (1) Lack of multi-dimensional constraint linkage verification mechanism: Existing methods only focus on the single indicator of the capacity margin of the transformer area, and do not include key indicators related to power quality and grid safety such as voltage deviation, harmonic current, and reverse load rate into the constraint system, resulting in one-sided evaluation results and easy to cause operational risks such as grid overload and power quality exceeding standards after the charging pile is connected.

[0003] (2) Inability to achieve precise access control at the node level: Existing technologies focus on the overall carrying capacity assessment of the distribution area, making it difficult to accurately calculate the capacity of charging piles that can be accessed at each node of the distribution area. This makes it impossible to provide precise support for the node-level site selection and capacity determination of charging piles, resulting in an unreasonable layout of charging pile access and affecting the operating efficiency of the distribution network.

[0004] (3) Difficulty in automatically generating adaptation improvement schemes: When the charging pile access capacity is insufficient, the existing method can only indicate that the capacity is insufficient. It cannot automatically generate a targeted capacity optimization and improvement scheme based on the actual operation of the substation area. It needs to be manually compiled, resulting in low efficiency, poor adaptability, and inability to quickly respond to the large-scale access needs of charging piles.

[0005] (4) Insufficient fit of the assessment model: Existing load capacity assessment models mostly use traditional algorithms and do not make full use of the predictive value of historical data, resulting in insufficient dynamism and accuracy of the assessment results, making it difficult to adapt to the characteristics of large load fluctuations and diverse access scenarios of charging piles.

[0006] Therefore, based on the aforementioned industry pain points and policy requirements, there is an urgent need to provide a dynamic evaluation and planning system that can achieve multi-constraint linkage verification, node-level accurate assessment, and intelligent generation of optimization and improvement solutions to support the safe and orderly access of charging piles, thereby promoting the high-quality development of the power distribution network. Summary of the Invention

[0007] The purpose of this invention is to provide a dynamic assessment and intelligent planning system and method for the carrying capacity of charging piles in power distribution network areas, in order to solve the problems existing in the prior art, such as the lack of a multi-dimensional constraint linkage verification mechanism, the inability to achieve precise node-level access control, the difficulty in automatically generating adaptation improvement schemes, and the insufficient fit of the assessment model.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, a dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area is provided, including: The data input module is used to acquire charging pile evaluation and planning data and send it to the dynamic evaluation module. The charging pile evaluation and planning data includes distribution network parameters, load data and historical distribution network data. The dynamic evaluation module is used to calculate the maximum load capacity of charging piles that can be connected to the target distribution area in the distribution network based on load data and distribution network parameters, and to perform load forecasting for the target distribution area based on historical data of the distribution network. Based on the load forecast data and the maximum load capacity of charging piles that can be connected to the distribution area, the module dynamically updates the remaining load capacity of each node in the target distribution area, so as to output charging pile hierarchical access suggestions for each node based on the remaining load capacity of each node. The intelligent planning module is used to obtain candidate planning schemes for charging piles and send them to the multi-constraint linkage verification module. The multi-constraint linkage verification module is used to simulate the charging pile access area based on the candidate planning scheme of the charging pile, so as to simulate the running status data of each specified node in the target area after the charging pile is connected to the target area. The multi-constraint linkage verification module is also used to calculate the access index of each specified node based on the data of each operating status, and to obtain the multi-constraint verification result of the candidate planning scheme of the charging pile based on each access index and send it to the intelligent planning module. The access index of any specified node includes the voltage deviation, reverse load rate, voltage per unit value and harmonic current of any specified node. The intelligent planning module is also used to update the candidate planning scheme of charging piles based on the results of multi-constraint verification, and resend the updated candidate planning scheme of charging piles to the multi-constraint linkage verification module until the planning convergence condition is met, and then obtain the optimal planning scheme of charging piles. The scheme generation module is used to generate the optimal carrying capacity improvement scheme for the target area based on the charging pile access carrying capacity analysis results and the optimal charging pile planning scheme, as well as the multi-constraint verification results and the corresponding operation status data of each specified node corresponding to the optimal charging pile planning scheme, and to use the pre-built scheme intelligent assistance to compile a large model. The charging pile access carrying capacity analysis results include the charging pile hierarchical access suggestions for each node. The results output module is used to visualize the charging pile access load capacity analysis results, the optimal load capacity improvement scheme, the optimal charging pile planning scheme, and the multi-constraint verification results corresponding to the optimal charging pile planning scheme.

[0009] Based on the aforementioned disclosure, this invention first calculates the maximum load capacity of available charging piles in the target distribution area using load data and distribution network parameters. Then, it uses historical distribution network data to predict the load of the target distribution area. Based on the load prediction results and the previously calculated maximum load capacity of available charging piles in the area, it dynamically updates the remaining available load capacity of each node in the target distribution area. Based on the remaining available load capacity of each node, it outputs tiered access recommendations for charging piles at each node. Thus, this invention fully utilizes the predictive value of historical data for load prediction, thereby improving the dynamism and accuracy of the evaluation results. Furthermore, by dynamically updating the remaining available load capacity of each node using load prediction and real-time data, and outputting tiered access recommendations, it achieves an upgrade from coarse estimation of the distribution area to precise control at the node level. This effectively optimizes the spatial layout of charging piles and improves the distribution network efficiency. This invention improves grid operating efficiency. Furthermore, by constructing a multi-dimensional linkage verification mechanism encompassing constraints such as voltage deviation, harmonic current, and reverse load rate, it evaluates candidate planning schemes for charging piles. This overcomes the limitations of traditional single-capacity assessment, comprehensively identifying power quality and safety risks after charging pile access, thus preventing grid overload and exceeding standards accidents from the outset. Finally, based on the aforementioned data, it automatically calls upon a large model to generate targeted optimization and improvement schemes, replacing inefficient manual compilation. This significantly shortens the response cycle, adapting to the needs of large-scale and rapid charging pile access. Therefore, this invention provides a dynamic evaluation and planning system capable of multi-constraint linkage verification, precise node-level evaluation, and intelligent generation of optimization and improvement schemes. It supports the safe and orderly access of charging piles and promotes high-quality development of the distribution network, making it highly suitable for large-scale application and promotion.

[0010] In one possible design, the power distribution network parameters include: the rated capacity of the main transformer, the load data includes the rated power of the transformer substation base load, and the historical data of the power distribution network includes historical load data and historical charging pile access and operation data; The dynamic evaluation module is used to calculate the maximum load capacity of the target transformer area that can be connected to charging piles based on the rated capacity of the main transformer and the rated power of the transformer area's basic load. The dynamic evaluation module is used to input historical load data and historical charging pile access operation data into the load prediction model to obtain the user basic load prediction data and electric vehicle charging load prediction data of the target area within a preset time period. Based on the user basic load prediction data and electric vehicle charging load prediction data, the load prediction data is determined and used as the current actual operating load. The dynamic evaluation module is also used to calculate the remaining available load of the target substation based on the current actual operating load and the maximum available charging pile load of the substation, and to dynamically update the remaining available load of each node in the target substation based on the remaining available load of the substation.

[0011] In one possible design, when the maximum load capacity of the target transformer substation that can be connected to charging piles is calculated based on the rated capacity of the main transformer and the rated power of the substation's foundation load, the dynamic evaluation module is configured as follows: The maximum load capacity of the charging piles that can be connected to the transformer substation is calculated according to the following formula; ; In the formula, This indicates the maximum load capacity of charging piles that can be connected to the aforementioned transformer area. This indicates the rated capacity of the main transformer. The overall power factor of the transformer area. This indicates the rated power of the base load of the transformer substation; Accordingly, when calculating the remaining available load of the target substation based on the current actual operating load and the maximum available charging pile load of the substation area, the dynamic evaluation module is configured as follows: The remaining connectable load of the target transformer area is calculated according to the following formula; ; In the formula, This indicates the remaining connectable load in the aforementioned transformer area. This indicates the current actual operating load.

[0012] In one possible design, the distribution network parameters also include: distribution network topology data; Specifically, when dynamically updating the remaining available load of each node in the target distribution area based on the remaining available load of the distribution area, the dynamic evaluation module is configured as follows: Based on the distribution network topology data, identify each node in the target distribution area, and obtain the historical total load of the target distribution area and the historical load of each node. Based on the historical total load and the historical load of each node, the load ratio coefficient of each node is calculated. Using the load ratio coefficient and the remaining available load in the transformer area, the allocated load for each node is calculated. Obtain the actual load of each node, and determine the remaining available load of each node based on the allocated access load of each node and the actual load of each node.

[0013] In one possible design, the operating status data includes: the voltage amplitude of each specified node and the reverse transmission power of each specified node; Specifically, when calculating the access metrics for each specified node based on various operational status data, the multi-constraint linkage verification module is configured as follows: For any given node, obtain the rated voltage of that given node; Calculate the voltage deviation and per-unit voltage value of any specified node based on the rated voltage and the voltage amplitude of any specified node. Based on the reverse transmission power of any specified node, calculate the reverse load rate of any specified node. Obtain the harmonic parameters and charging pile access capacity of the charging pile connected to any of the specified nodes, and calculate the harmonic current of the specified node based on the rated voltage, the harmonic parameters and the charging pile access capacity. The access index of any specified node is formed by using the voltage deviation, per-unit voltage value, reverse load rate and harmonic current of any specified node.

[0014] In one possible design, when calculating the voltage deviation and per-unit value of any specified node based on the rated voltage and the voltage amplitude of any specified node, the multi-constraint linkage verification module is configured as follows: The ratio between the voltage amplitude of any specified node and the rated voltage is taken as the voltage per unit value; Based on the rated voltage and the voltage amplitude of any specified node, the voltage deviation of any specified node is calculated according to the following formula; ; In the formula, This represents the voltage deviation at any of the specified nodes. This represents the voltage amplitude of any specified node. This represents the rated voltage of any of the specified nodes.

[0015] In one possible design, when the reverse load rate of any specified node is calculated based on the reverse transmission power of any specified node, the multi-constraint linkage verification module is configured as follows: Obtain the actual total operating load of the target transformer area before simulated access; Based on the actual total operating load and the reverse transmission power of any designated node, the reverse load rate of any designated node is calculated using the following formula. ; This represents the reverse load rate of any specified node. This represents the reverse transmission power of any of the specified nodes. This indicates the actual total operating load.

[0016] In one possible design, when the multi-constraint verification results of the candidate charging pile planning scheme are obtained based on various access indicators, the multi-constraint linkage verification module is configured as follows: Obtain the indicator constraint parameters for each specified node; For any given node, determine whether the voltage deviation, per-unit voltage, reverse load rate, and harmonic current of the given node all meet the index constraint parameters of the given node. If yes, then the verification result of the charging pile access planning scheme of any designated node in the candidate charging pile planning scheme is determined to be feasible; otherwise, the verification result of the charging pile access planning scheme of any designated node in the candidate charging pile planning scheme is determined to be infeasible. After all designated nodes have been traversed, the verification results of the charging pile access planning scheme of each designated node are used to form the multi-constraint verification result. Accordingly, when updating the candidate planning scheme for charging piles based on the multi-constraint verification results, the intelligent planning module is configured as follows: Based on the results of the multi-constraint verification, the nodes that are deemed infeasible for access in the charging pile access planning scheme are identified as nodes to be adjusted. A single-parameter iterative trial method is used to adjust the charging pile access capacity corresponding to each node to be adjusted, so as to obtain the updated charging pile candidate planning scheme after adjustment.

[0017] In one possible design, the historical data of the distribution network also includes: historical survey information and historical planning schemes. The intelligent auxiliary model for scheme compilation is trained based on historical survey information, historical planning schemes, historical carrying capacity analysis results, multi-constraint verification results of historical planning schemes, and the corresponding operating status data of each node.

[0018] Secondly, a method for dynamic assessment and intelligent planning of charging pile carrying capacity in a power distribution network area is provided. This method is implemented based on the dynamic assessment and intelligent planning system for charging pile carrying capacity in the power distribution network area, or any possible design of the first aspect, and includes: Obtain charging pile assessment and planning data, which includes distribution network parameters, load data, and historical distribution network data; Based on load data and distribution network parameters, the maximum load capacity of charging piles that can be connected to the target distribution area in the distribution network is calculated. Based on historical data of the distribution network, the load of the target distribution area is predicted. According to the load prediction data and the maximum load capacity of charging piles that can be connected to the distribution area, the remaining load capacity of each node in the target distribution area is dynamically updated. Based on the remaining load capacity of each node, a charging pile hierarchical access suggestion is output for each node. Obtain candidate planning schemes for charging piles; Based on the candidate planning schemes for charging piles, a simulation of the charging pile access area is conducted to obtain the operating status data of each specified node in the target area after the charging piles are connected to the target area. Based on the various operating status data, the access indicators of each specified node are calculated, and based on the access indicators, the multi-constraint verification results of the candidate planning scheme for charging piles are obtained. The access indicators of any specified node include the voltage deviation, reverse load rate, voltage per unit value and harmonic current of that specified node. Based on the results of the multi-constraint verification, the candidate planning scheme for charging piles is updated, and the charging pile access area is simulated again based on the updated candidate planning scheme until the planning convergence condition is met, and the optimal planning scheme for charging piles is obtained. Based on the charging pile access carrying capacity analysis results and the optimal charging pile planning scheme, as well as the multi-constraint verification results and the corresponding operation status data of each specified node corresponding to the optimal charging pile planning scheme, and using the pre-built scheme to intelligently assist in compiling a large model, the optimal carrying capacity improvement scheme for the target area is generated. The charging pile access carrying capacity analysis results include the charging pile hierarchical access suggestions for each node. The results of the charging pile access load capacity analysis, the optimal load capacity improvement scheme, the optimal charging pile planning scheme, and the multi-constraint verification results corresponding to the optimal charging pile planning scheme are visualized.

[0019] Thirdly, a device for dynamic assessment and intelligent planning of charging pile carrying capacity in a power distribution network area is provided. Taking the device as an electronic device as an example, it includes a memory, a processor, and a transceiver that are connected in sequence. The memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the dynamic assessment and intelligent planning method for charging pile carrying capacity in a power distribution network area as described in the second aspect.

[0020] Fourthly, a storage medium is provided, on which instructions are stored. When the instructions are executed on a computer, the dynamic assessment and intelligent planning method for the carrying capacity of charging piles in the distribution network area as described in the second aspect is performed.

[0021] Fifthly, a computer program product containing instructions is provided, which, when executed on a computer, causes the computer to perform the dynamic assessment and intelligent planning method for the carrying capacity of charging piles in the distribution network area as described in the second aspect.

[0022] Beneficial effects: (1) Multi-constraint linkage verification improves the accuracy of evaluation: A multi-dimensional constraint system covering voltage deviation, harmonic current and reverse load rate is constructed to realize multi-index linkage verification. In this way, the one-sidedness of single index evaluation can be avoided, and the operational risks such as grid overload and power quality exceeding the standard after the charging pile is connected can be effectively avoided.

[0023] (2) Precise node-level control and adaptability to diverse scenarios: Based on the distribution network topology, the carrying capacity of each node is accurately calculated, realizing the node-level site selection and capacity determination of charging piles, adapting to various application scenarios such as site selection and capacity determination, and node maximum capacity assessment, which can meet the planning needs of different users.

[0024] (3) Intelligent generation of improvement schemes to improve planning efficiency: By constructing an intelligent assisted large model, a highly adaptable carrying capacity improvement scheme is automatically generated. In this way, there is no need for tedious manual compilation, which greatly shortens the planning cycle and reduces labor costs.

[0025] (4) Strong dynamic adaptability and fits the actual operation scenario: Based on the load prediction model, the load prediction and carrying capacity are dynamically updated, which can adapt to the characteristics of large load fluctuation of charging piles. At the same time, it supports flexible parameter configuration and can adapt to different scales and types of distribution network areas.

[0026] (5) High policy fit and support for high-quality development: Strictly implement the requirements of relevant policies since 2024 on the power quality management of charging pile access, support the safe and orderly access of charging piles, promote the upgrading of distribution network areas to intelligence and efficiency, and meet the requirements of high-quality development of distribution network of new power system. Attached Figure Description

[0027] Figure 1 This is a structural diagram of the dynamic evaluation and intelligent planning system for the carrying capacity of charging piles in a power distribution network area provided in an embodiment of the present invention; Figure 2 A flowchart of the dynamic evaluation and intelligent planning method for the carrying capacity of charging piles in power distribution network areas provided in an embodiment of the present invention. Detailed Implementation

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0029] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0030] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0031] Example: See Figure 1 As shown, the dynamic assessment and intelligent planning system for the carrying capacity of charging piles in the distribution network provided in this embodiment relies on the full-link topology architecture of the distribution network substation-line-distribution area to construct a full-process system of "dynamic assessment-feasibility verification-optimization and improvement". The system includes a data input module, a dynamic assessment module, a multi-constraint linkage verification module, an intelligent planning module, a scheme generation module, and a result output module. The modules work together to complete the entire process of charging pile carrying capacity assessment and planning.

[0032] In practical applications, the detailed working process of each of the aforementioned modules is as follows: In this embodiment, the data input module is used to acquire charging pile evaluation and planning data. The charging pile evaluation and planning data includes various basic data, parameters, and historical data required for system operation. Specifically, it may include, but is not limited to, distribution network parameters, load data, and historical distribution network data. Furthermore, the charging evaluation and planning data may also include charging pile-related parameters, constraint parameters, algorithm and model parameters, etc. In this way, the aforementioned data can provide data support for subsequent evaluation, verification, and planning.

[0033] Furthermore, examples of distribution network parameters may include, but are not limited to, distribution network topology data (i.e., the full-link topology data of distribution network substation-line-transformer area, that is, the hierarchical relationship of distribution network substation-line-transformer area-low-voltage branch box-user node), line parameters, rated capacity of main transformer, load rate, etc.; at the same time, examples of load data may include, but are not limited to, rated power of transformer area basic load, user basic load curve and electric vehicle charging load demand curve, etc.; historical data of distribution network may include, but are not limited to, historical load data, historical charging pile access and operation data, historical survey information and historical planning schemes, etc.

[0034] Furthermore, for example, the parameters related to charging piles may include, but are not limited to: upper and lower limits of installed capacity, designated test nodes, capacity trial step size, maximum trial capacity, etc.; constraint parameters may include, but are not limited to: upper and lower limits of voltage deviation safety, harmonic current limit, reverse load rate limit, voltage per unit value limit, etc.; and algorithm and model parameters may include, but are not limited to: GRU-Infomer-attention model parameters, training parameters for intelligent assistance in compiling large models, etc.

[0035] Thus, after obtaining the aforementioned charging pile assessment and planning data, it can be sent to the dynamic assessment module to conduct a dynamic assessment of the charging pile carrying capacity of the distribution network area.

[0036] In this embodiment, the module relies on the GRU-Infomer-attention model to realize the dynamic assessment of the charging pile carrying capacity of the distribution network area. That is, the dynamic assessment module is used to calculate the maximum load capacity of the charging piles that can be connected to the target area in the distribution network based on load data and distribution network parameters, and to perform load prediction of the target area based on historical data of the distribution network. Based on the load prediction data and the maximum load capacity of the charging piles that can be connected to the target area, the remaining load capacity of each node in the target area is dynamically updated, so as to output the charging pile hierarchical access suggestions for each node based on the remaining load capacity of each node.

[0037] In practical applications, the following is a detailed implementation process of the dynamic evaluation module for dynamically evaluating the load-bearing capacity of charging piles: The dynamic evaluation module first calculates the maximum load capacity of the target transformer substation based on the rated capacity of the main transformer and the rated power of the substation base load. Optionally, for example, but not limited to, the following formula can be used to calculate the maximum load capacity of the substation.

[0038] ; In the formula, This indicates the maximum load capacity of charging piles that can be connected to the aforementioned transformer area. This indicates the rated capacity of the main transformer. This is the overall power factor of the transformer area (a preset value). This indicates the rated power of the base load of the transformer substation.

[0039] Thus, after calculating the maximum load capacity of charging piles that can be connected to the target distribution area, historical data of the distribution network can be used, along with a load forecasting model, to predict the load of the target distribution area. The dynamic evaluation module inputs historical load data and historical charging pile access operation data into the load prediction model to obtain user basic load prediction data and electric vehicle charging load prediction data for the target area within a preset time period. Based on the user basic load prediction data and electric vehicle charging load prediction data, the module determines the load prediction data and uses the load prediction data as the current actual operating load.

[0040] In this embodiment, the load forecasting model can be, but is not limited to, the trained GRU-Infomer-attention model. By using this model and combining it with historical load data and historical charging pile access and operation data, load forecasting can make full use of the predictive value of historical data of the distribution network, thereby improving the dynamism and accuracy of carrying capacity assessment.

[0041] Meanwhile, for example, but not limited to, summing user base load forecast data and electric vehicle charging load forecast data, load forecast data can be obtained (the forecast data is a sequence, therefore, the load forecast data is also a sequence). After obtaining the load forecast data, it can be used as the current actual operating load. Combined with the previously calculated maximum connectable charging pile load of the transformer substation, the remaining connectable load of the target substation can be obtained, and the remaining connectable load of the nodes in the target substation can be dynamically updated. The process is as follows: The dynamic evaluation module is also used to calculate the remaining available load of the target substation based on the current actual operating load and the maximum available charging pile load of the substation, and to dynamically update the remaining available load of each node in the target substation based on the remaining available load of the substation.

[0042] In specific implementation, for example, but not limited to, the remaining connectable load of the target transformer area can be calculated according to the following formula.

[0043] ; In the formula, This indicates the remaining connectable load in the aforementioned transformer area. This represents the current actual operating load. In this embodiment, the aforementioned formula is performed on a prediction period. For example, if the current actual operating load of the future t-th period is substituted into the aforementioned formula, the remaining connectable load of the transformer area at the future t-th period is obtained.

[0044] Thus, based on the aforementioned formula, after calculating the remaining available load in the distribution area, the remaining available load of each node can be dynamically updated, so as to output charging pile hierarchical access suggestions for each node in the distribution area.

[0045] Optionally, this embodiment uses distribution network topology data to dynamically update the remaining connectable load of nodes and outputs corresponding charging pile hierarchical access suggestions. That is, when dynamically updating the remaining connectable load of each node in the target distribution area based on the remaining connectable load of the distribution area, the dynamic evaluation module is configured to perform the following operations: Step 1: Based on the distribution network topology data, identify each node in the target distribution area and obtain the historical total load of the target distribution area and the historical load of each node.

[0046] In practical implementation, a node topology adjacency table can be established based on the distribution network topology data, that is, based on the hierarchical relationship of distribution network substation-line-transformer area-low voltage branch box-user node; then, based on the node topology adjacency table, the set of all end nodes in the target transformer area that can be connected to charging piles is determined; then, the current carrying capacity limit of the upper-level line corresponding to each node is recorded as the physical upper limit of the node.

[0047] Once the nodes in the target distribution area are identified, historical operating data for the past 30 days (or the same period in the same season) can be obtained (the granularity of which is the same as the granularity of the prediction period of the prediction sequence), that is, the historical load of each node and the historical total load corresponding to the target distribution area can be obtained. Then, based on the historical data obtained above, the load ratio coefficient of each node can be calculated, as shown in the second step below.

[0048] Step 2: Calculate the load ratio of each node based on the historical total load and the historical load of each node. In this embodiment, for any node, for example, but not limited to, the ratio between the historical load of that node and the historical total load of the target area can be used as the load ratio of that node. For example, for the future time period t, the ratio between the historical load of the node at the historical time period t and the historical total load at the historical time period t can be used as the load ratio of the future time period t.

[0049] Based on the aforementioned steps, after calculating the load ratio coefficient of each node, the allocated access load of each node can be calculated by combining the remaining accessible load of the transformer area calculated above. The process is shown in the third step below.

[0050] Step 3: Calculate the allocated access load for each node using the load ratio coefficient and the remaining available access load of the transformer area. In practice, multiply the load ratio coefficient of each node by the remaining available access load of the transformer area to obtain the initial allocated load for each node. Then, for any node, select the minimum value from the initial allocated load of that node and its corresponding physical upper limit to use as the allocated access load for that node (of course, it is also calculated with the future prediction period t as the granularity).

[0051] Thus, after calculating the allocated access load of each node based on the aforementioned steps, the remaining access load of each node can be dynamically updated, as shown in step four below.

[0052] Step 4: Obtain the actual load of each node, and determine the remaining available load of each node based on the allocated access load and the actual load of each node. In this embodiment, as previously explained, the prediction and load update are performed at the granularity of future prediction time periods. Therefore, when the target area operates to the future time period t, the actual load of each node at time period t is obtained. Then, the allocated access load at time period t is subtracted from the actual load to obtain the corresponding remaining available load. Subsequently, as the target area operates to different future time periods, the corresponding actual load is collected in real time, and the remaining available load of each node in future time periods can be continuously updated.

[0053] Therefore, after obtaining the remaining connectable load of each node through the aforementioned first to fourth steps, we can output a tiered access suggestion for charging piles for each node based on this.

[0054] In practical applications, for any given node, the minimum remaining load of that node within a complete future cycle (e.g., 24 hours) can be used as the grading benchmark, but is not limited to: if the minimum remaining connectable load of any given node is ≥100kW, the grading access recommendation is direct access; if the minimum remaining connectable load of any given node is greater than or equal to 30kW but less than 100kW, the grading access recommendation is to control the access capacity; and if the minimum remaining connectable load of any given node is less than 30kW, the grading access recommendation is not to access.

[0055] In this way, the remaining available load capacity of the aforementioned transformer area and the charging pile hierarchical access recommendations for each node can be used to form the charging pile access carrying capacity analysis results.

[0056] After completing the charging pile access capacity analysis, the optimal planning scheme for charging piles can be derived by using a multi-constraint linkage verification module and an intelligent planning module, and by introducing a multi-dimensional verification mechanism. The process is as follows: The intelligent planning module is used to obtain candidate planning schemes for charging piles and send them to the multi-constraint linkage verification module. In this embodiment, the candidate planning scheme for charging piles can be generated based on the charging pile hierarchical access suggestions of the aforementioned nodes. That is, the candidate planning scheme for charging piles can include, but is not limited to, the charging pile access planning schemes of each specified node. The charging pile access planning scheme of any specified node includes the charging pile access capacity of that specified node (which is an initial value when planning begins). Among them, nodes with hierarchical access suggestions of direct access and access capacity control are selected from the target substation area and designated as specified nodes.

[0057] Thus, after obtaining the candidate planning scheme for charging piles, a multi-constraint linkage verification module can be used to perform multi-dimensional verification of the planning scheme. That is, the multi-constraint linkage verification module is used to simulate the charging pile access area based on the candidate planning scheme for charging piles, so as to simulate the operating status data of each specified node in the target area after the charging piles are connected to the target area. In this embodiment, for example, but not limited to, the grid operating status after the charging piles are connected can be simulated based on power flow calculation (three-phase symmetry assumption). That is, the charging pile load is connected to the corresponding specified node as a new PQ node; then, the forward-backward substitution method is used to perform power flow calculation, and finally, the voltage amplitude of each specified node and the reverse transmission power of each specified node can be output as verification status indicators.

[0058] After obtaining the running status data of each specified node, a multi-dimensional constraint linkage verification mechanism can be used to perform multi-dimensional verification of each specified node, namely: The multi-constraint linkage verification module is also used to calculate the access indicators of each specified node based on the data of each operating status, and to obtain the multi-constraint verification results of the candidate planning scheme of the charging pile based on each access indicator and send them to the intelligent planning module. The access indicators of any specified node include the voltage deviation, reverse load rate, voltage per unit value and harmonic current of any specified node.

[0059] In practical applications, when calculating the access metrics for each specified node based on various operational status data, the multi-constraint linkage verification module is configured to perform the following operations: Step 1: For any given node, obtain the rated voltage of that given node.

[0060] Step 2: Calculate the voltage deviation and per-unit value of any specified node based on the rated voltage and the voltage amplitude of any specified node. In this embodiment, for example, but not limited to, the ratio between the voltage amplitude of any specified node and the rated voltage can be used as the per-unit value. Then, the voltage deviation of any specified node can be calculated based on the rated voltage and the voltage amplitude of any specified node according to the following formula.

[0061] ; In the formula, This represents the voltage deviation at any of the specified nodes. This represents the voltage amplitude of any specified node. This represents the rated voltage of any of the specified nodes.

[0062] After calculating the voltage deviation and per-unit voltage value of any specified node, the reverse load rate can be calculated, as shown in step 3 below.

[0063] Step 3: Calculate the reverse load rate of any specified node based on the reverse transmission power of any specified node. In specific applications, for example, but not limited to, first obtain the actual total operating load of the target area before simulated access; then, according to the actual total operating load and the reverse transmission power of any specified node, calculate the reverse load rate of any specified node using the following formula.

[0064] ; This represents the reverse load rate of any specified node. This represents the reverse transmission power of any of the specified nodes. This indicates the actual total operating load.

[0065] After calculating the reverse transmission power, the harmonic current can be calculated, as shown in step 4 below.

[0066] Step 4: Obtain the harmonic parameters and charging pile access capacity of the charging pile connected to any of the specified nodes, and calculate the harmonic current of the specified node based on the rated voltage, the harmonic parameters, and the charging pile access capacity. In this embodiment, the harmonic parameter can be, but is not limited to, the harmonic content rate of the charging pile corresponding to the specified node, which can be obtained from a harmonic spectrum database. The harmonic frequency database stores the harmonic content rate corresponding to the harmonic order of the current of different charging piles. When using it, the harmonic order of the current of the specified node can be matched in the database.

[0067] In this embodiment, the fundamental current of any specified node can be calculated first, but is not limited to, based on the charging pile's access capacity and rated voltage. That is, the product between the rated power supply and the fundamental power factor (typically between 0.95 and 0.98) of the charging pile corresponding to any specified node is first calculated, and then the product is multiplied by... The total product is obtained; finally, the ratio between the charging pile access capacity and the total product is used as the fundamental current.

[0068] After obtaining the fundamental current, the product of the fundamental current and the harmonic content rate can be used as the harmonic current.

[0069] After calculating the harmonic current of any given node, the three indicators mentioned above can be combined to form the access indicators of any given node, as shown in step 5 below.

[0070] Step 5: Using the voltage deviation, per-unit voltage, reverse load rate, and harmonic current of any designated node, construct the access index of any designated node.

[0071] Based on the aforementioned steps, after calculating the access indicators for each specified node, multi-constraint verification of the charging pile candidate planning scheme can be performed. Specifically, when the multi-constraint verification results of the charging pile candidate planning scheme are obtained based on the various access indicators, the multi-constraint linkage verification module is configured to perform the following operations: Step 6: Obtain the indicator constraint parameters of each specified node; In this embodiment, the indicator constraint parameters of any specified node are the constraint parameters in the aforementioned charging pile evaluation and planning data, and correspond to the constraint parameters (i.e. indicator thresholds) of the four indicators respectively; Of course, the indicator thresholds of the aforementioned four indicators can be specifically set according to actual use, and this embodiment does not make specific limitations.

[0072] Thus, after obtaining the indicator constraint parameters of each specified node, multi-constraint verification can be performed based on these parameters, as shown in steps 7 and 8 below.

[0073] Step 7: For any specified node, determine whether the voltage deviation, per-unit voltage, reverse load rate, and harmonic current of the specified node all meet the index constraint parameters of the specified node.

[0074] Step 8: If yes, then determine that the verification result of the charging pile access planning scheme of any designated node in the candidate charging pile planning scheme is feasible; otherwise, determine that the verification result of the charging pile access planning scheme of any designated node in the candidate charging pile planning scheme is not feasible. After all designated nodes have been traversed, the verification results of the charging pile access planning schemes of each designated node are used to form the multi-constraint verification result.

[0075] In this embodiment, if all indicators are within the corresponding constraint range (i.e., meet the corresponding indicator threshold), it is determined that the charging pile access of any specified node is feasible; if any indicator exceeds the constraint range, it is determined that the access is not feasible, and the exceeding indicator and the degree of exceeding the standard are identified.

[0076] After completing the multi-constraint verification of each specified node through the above steps, the multi-constraint verification results of the charging pile candidate planning scheme can be generated. Then, based on these results, the charging pile candidate planning scheme can be optimized, i.e.: The intelligent planning module is also used to update the candidate planning schemes for charging piles based on the results of multi-constraint verification, and resend the updated candidate planning schemes for charging piles to the multi-constraint linkage verification module until the planning convergence conditions are met, thus obtaining the optimal planning scheme for charging piles.

[0077] In practical applications, when updating the candidate planning scheme for charging piles based on the results of multi-constraint verification, the intelligent planning module is configured to: first, based on the results of multi-constraint verification, determine the designated nodes whose verification results for the charging pile access planning scheme are infeasible, and use them as nodes to be adjusted; then, use a single-parameter iterative trial method to adjust the charging pile access capacity corresponding to each node to be adjusted, so as to obtain the updated candidate planning scheme for charging piles after adjustment.

[0078] In practice, the charging pile access capacity of each designated node can be gradually reduced based on the capacity trial step size in the relevant parameters of the charging pile. After adjustment, an updated charging pile access planning scheme for each designated node can be obtained. Then, an updated candidate charging pile planning scheme can be obtained using the updated charging pile access planning schemes. Finally, the updated candidate charging pile planning scheme can be sent to the multi-constraint linkage verification module for multi-dimensional verification. This process continuously reduces the corresponding charging pile access capacity according to the capacity trial step size until the planning convergence condition is met, thus obtaining the optimal charging pile planning scheme.

[0079] For example, the convergence condition of the planning is that the charging pile access planning schemes for each specified node pass the multi-constraint verification or reach the maximum number of iterations. When the maximum number of iterations is reached, if there are still specified nodes in the candidate charging pile planning schemes whose verification results are not feasible for access, the user is prompted to adjust the access node or directly delete the scheme corresponding to the specified node that is not feasible for access. That is, the charging pile access planning schemes with the verification results of feasible access to the specified nodes form the optimal planning scheme.

[0080] After completing the intelligent planning of charging piles, the optimal carrying capacity improvement plan can be generated using the solution generation module. The process is as follows: The scheme generation module is used to generate the optimal carrying capacity improvement scheme for the target substation area based on the charging pile access carrying capacity analysis results, the optimal charging pile planning scheme, the multi-constraint verification results corresponding to the optimal charging pile planning scheme, and the corresponding operation status data of each specified node, and to use the pre-built scheme intelligent assistance to compile a large model. The charging pile access carrying capacity analysis results include the charging pile hierarchical access suggestions for each node and the remaining connectable load of the substation area.

[0081] In practical applications, the intelligent auxiliary model for scheme development is trained based on historical survey information, historical planning schemes, historical carrying capacity analysis results, and the multi-constraint verification results of historical planning schemes, as well as the corresponding operational status data of each node. Specifically, the model uses historical survey information as input, historical planning schemes as labels, and historical carrying capacity analysis results, multi-constraint verification results of historical planning schemes, and the corresponding operational status data of each node as context for input prompts to train a large language model (LLM), thereby obtaining the intelligent auxiliary model for scheme development.

[0082] In practical use, the actual survey information of the target area is obtained and then used as the model input data. The charging pile access load capacity analysis results, the optimal charging pile planning scheme, the multi-constraint verification results corresponding to the optimal charging pile planning scheme, and the corresponding operation status data of each specified node are used as input prompt context to input into the trained LLM, thereby obtaining the optimal load capacity improvement scheme.

[0083] Optional, optimal capacity enhancement solutions may include, but are not limited to: Analysis of operational shortcomings in the transformer substation: identifying the current shortcomings and causes in terms of capacity, power quality, and safe operation; Optimal planning path: providing the optimal access layout and capacity configuration scheme for charging piles based on node-level assessment results; Optimal load absorption method: providing load absorption optimization schemes to improve load utilization, taking into account the characteristics of charging load fluctuations; and recommendations for substation expansion: providing reasonable expansion and renovation schemes for substations with insufficient capacity.

[0084] The analysis of operational shortcomings in the transformer substation is as follows: based on the load capacity assessment results, identify the indicators exceeding the standards and the corresponding equipment / nodes; the optimal planning path is: based on the node-level load capacity assessment results, recommend the node with the largest remaining capacity as the access point; the expansion suggestion for the transformer substation is: calculate the required expansion capacity based on the load rate of the main transformer / line exceeding the standard.

[0085] After obtaining the optimal carrying capacity improvement scheme, the aforementioned charging pile access carrying capacity analysis results, the optimal charging pile planning scheme, and the multi-constraint verification results corresponding to the optimal charging pile planning scheme can be visualized, that is: The results output module is used to visualize the charging pile access load capacity analysis results, the optimal load capacity improvement scheme, the optimal charging pile planning scheme, and the multi-constraint verification results corresponding to the optimal charging pile planning scheme.

[0086] In practical implementation, this module will output dynamic evaluation results, intelligent planning results, multi-constraint verification results, and optimization and improvement schemes in text and / or chart form for easy viewing and decision-making by users. Specific output content includes: Charging pile access capacity assessment results: maximum load capacity that can be connected to the distribution area, remaining load capacity that can be connected, and hierarchical access recommendations for each node; Intelligent planning results: optimal installation node and optimal capacity of charging piles, and feasibility judgment results for charging pile access (i.e., multi-constraint verification); Operation monitoring results: load change curve of charging piles within one day, voltage change curve of distribution network nodes, voltage per unit value, voltage deviation, harmonic current and other indicator data; Optimization and improvement plan: complete capacity improvement plan.

[0087] Thus, outputting the aforementioned content in text and / or chart form can assist users in managing the access of charging piles in the area.

[0088] Therefore, through the detailed description of the dynamic assessment and intelligent planning system for the carrying capacity of charging piles in distribution network areas, this invention breaks through the limitations of traditional single capacity assessment by constructing a linkage verification mechanism covering multiple dimensions of constraints such as voltage deviation, harmonic current, and reverse load rate. It can comprehensively identify the power quality and safety risks after charging piles are connected, thereby avoiding grid overload and exceeding standards accidents from the source. At the same time, by using load forecasting and real-time data to dynamically update the remaining connectable load of each node and output hierarchical access suggestions, it realizes the upgrade from coarse estimation of distribution areas to precise control at the node level, effectively optimizing the spatial layout of charging piles and improving the operating efficiency of distribution networks. In addition, based on the aforementioned data, the system automatically calls large models to generate targeted optimization and improvement schemes to replace inefficient manual compilation. This can significantly shorten the response cycle and adapt to the needs of large-scale and rapid access of charging piles. Furthermore, this invention makes full use of historical data for dynamic load forecasting, making the assessment results time-varying and forward-looking, better able to cope with random fluctuations in charging load and diverse application scenarios, and can provide solid technical support for the high-quality development of distribution networks. Therefore, this invention is very suitable for large-scale application and promotion.

[0089] like Figure 2 As shown, the second aspect of this embodiment provides a method for dynamic evaluation and intelligent planning of the carrying capacity of charging piles in a distribution network area. This method is implemented based on the dynamic evaluation and intelligent planning system for the carrying capacity of charging piles in a distribution network area described in the first aspect of the embodiment. The operation steps of this method may be, but are not limited to, the steps S1 to S8 below.

[0090] S1. Obtain charging pile assessment and planning data, which includes distribution network parameters, load data, and historical distribution network data.

[0091] S2. Based on load data and distribution network parameters, calculate the maximum load capacity of charging piles that can be connected to the target distribution area in the distribution network, and perform load forecasting for the target distribution area based on historical data of the distribution network. Then, based on the load forecast data and the maximum load capacity of charging piles that can be connected to the distribution area, dynamically update the remaining load capacity of each node in the target distribution area, so as to output charging pile hierarchical access suggestions for each node based on the remaining load capacity of each node.

[0092] S3. Obtain candidate planning schemes for charging piles.

[0093] S4. Based on the candidate planning schemes for charging piles, simulate the charging pile access area to obtain the operating status data of each specified node in the target area after the charging pile is connected to the target area.

[0094] S5. Based on the various operating status data, calculate the access indicators for each designated node, and based on the access indicators, obtain the multi-constraint verification results of the candidate planning scheme for charging piles. The access indicators for any designated node include the voltage deviation, reverse load rate, voltage per unit value, and harmonic current of that designated node.

[0095] S6. Based on the multi-constraint verification results, update the candidate planning scheme for charging piles, and re-simulate the charging pile access area based on the updated candidate planning scheme until the planning convergence condition is met, and obtain the optimal planning scheme for charging piles.

[0096] S7. Based on the charging pile access carrying capacity analysis results and the optimal charging pile planning scheme, as well as the multi-constraint verification results and the corresponding operation status data of each designated node corresponding to the optimal charging pile planning scheme, and using the pre-built scheme intelligent assistance to compile a large model, the optimal carrying capacity improvement scheme for the target area is generated. The charging pile access carrying capacity analysis results include charging pile hierarchical access suggestions for each node.

[0097] S8. Visualize the results of the charging pile access load capacity analysis, the optimal load capacity improvement scheme, the optimal charging pile planning scheme, and the multi-constraint verification results corresponding to the optimal charging pile planning scheme.

[0098] The working process, working details and technical effects of the method provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0099] The third aspect of this embodiment provides a device for dynamic evaluation and intelligent planning of the carrying capacity of charging piles in a power distribution network area. Taking the device's electronic equipment as an example, it includes: a memory, a processor, and a transceiver that are connected in sequence. The memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the dynamic evaluation and intelligent planning method for the carrying capacity of charging piles in a power distribution network area as described in the second aspect of this embodiment.

[0100] For specific examples, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor, also known as the CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0101] In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. For example, the processor may not be limited to microprocessors of the STM32F105 series, reduced instruction set computer (RISC) microprocessors, x86 architecture processors, or processors with integrated neural network processing units (NPUs). The transceiver may be, but is not limited to, a Wi-Fi transceiver, a Bluetooth transceiver, a General Packet Radio Service (GPRS) transceiver, a ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard) transceiver, a 3G transceiver, a 4G transceiver, and / or a 5G transceiver. Furthermore, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0102] The working process, working details and technical effects of the electronic device provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0103] The fourth aspect of this embodiment provides a storage medium that stores instructions containing the dynamic assessment and intelligent planning method for the carrying capacity of charging piles in the distribution network area as described in the second aspect of this embodiment. That is, the storage medium stores instructions, and when the instructions are run on a computer, the dynamic assessment and intelligent planning method for the carrying capacity of charging piles in the distribution network area as described in the second aspect of this embodiment is executed.

[0104] The storage medium refers to a carrier for storing data, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or memory sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0105] The working process, working details and technical effects of the storage medium provided in this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0106] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the dynamic assessment and intelligent planning method for the carrying capacity of charging piles in a power distribution network area as described in the second aspect of this embodiment. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0107] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area, characterized in that, include: The data input module is used to acquire charging pile evaluation and planning data and send it to the dynamic evaluation module. The charging pile evaluation and planning data includes distribution network parameters, load data and historical distribution network data. The dynamic evaluation module is used to calculate the maximum load capacity of charging piles that can be connected to the target distribution area in the distribution network based on load data and distribution network parameters, and to perform load forecasting for the target distribution area based on historical data of the distribution network. Based on the load forecast data and the maximum load capacity of charging piles that can be connected to the distribution area, the module dynamically updates the remaining load capacity of each node in the target distribution area, so as to output charging pile hierarchical access suggestions for each node based on the remaining load capacity of each node. The intelligent planning module is used to obtain candidate planning schemes for charging piles and send them to the multi-constraint linkage verification module. The multi-constraint linkage verification module is used to simulate the charging pile access area based on the candidate planning scheme of the charging pile, so as to simulate the running status data of each specified node in the target area after the charging pile is connected to the target area. The multi-constraint linkage verification module is also used to calculate the access index of each specified node based on the data of each operating status, and to obtain the multi-constraint verification result of the candidate planning scheme of the charging pile based on each access index and send it to the intelligent planning module. The access index of any specified node includes the voltage deviation, reverse load rate, voltage per unit value and harmonic current of any specified node. The intelligent planning module is also used to update the candidate planning scheme of charging piles based on the results of multi-constraint verification, and resend the updated candidate planning scheme of charging piles to the multi-constraint linkage verification module until the planning convergence condition is met, and then obtain the optimal planning scheme of charging piles. The scheme generation module is used to generate the optimal carrying capacity improvement scheme for the target area based on the charging pile access carrying capacity analysis results and the optimal charging pile planning scheme, as well as the multi-constraint verification results and the corresponding operation status data of each specified node corresponding to the optimal charging pile planning scheme, and to use the pre-built scheme intelligent assistance to compile a large model. The charging pile access carrying capacity analysis results include the charging pile hierarchical access suggestions for each node. The results output module is used to visualize the charging pile access load capacity analysis results, the optimal load capacity improvement scheme, the optimal charging pile planning scheme, and the multi-constraint verification results corresponding to the optimal charging pile planning scheme.

2. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 1, characterized in that, The power distribution network parameters include: the rated capacity of the main transformer, the load data includes the rated power of the basic load of the distribution area, and the historical data of the power distribution network includes historical load data and historical charging pile access and operation data; The dynamic evaluation module is used to calculate the maximum load capacity of the target transformer area that can be connected to charging piles based on the rated capacity of the main transformer and the rated power of the transformer area's basic load. The dynamic evaluation module is used to input historical load data and historical charging pile access operation data into the load prediction model to obtain the user basic load prediction data and electric vehicle charging load prediction data of the target area within a preset time period. Based on the user basic load prediction data and electric vehicle charging load prediction data, the load prediction data is determined and used as the current actual operating load. The dynamic evaluation module is also used to calculate the remaining available load of the target substation based on the current actual operating load and the maximum available charging pile load of the substation, and to dynamically update the remaining available load of each node in the target substation based on the remaining available load of the substation.

3. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 2, characterized in that, When the maximum load capacity of the target distribution area that can be connected to charging piles is calculated based on the rated capacity of the main transformer and the rated power of the distribution area's foundation load, the dynamic evaluation module is configured as follows: The maximum load capacity of the charging piles that can be connected to the transformer substation is calculated according to the following formula; ； In the formula, This indicates the maximum load capacity of charging piles that can be connected to the aforementioned transformer area. This indicates the rated capacity of the main transformer. The overall power factor of the transformer area. This indicates the rated power of the base load of the transformer substation; Accordingly, when calculating the remaining available load of the target substation based on the current actual operating load and the maximum available charging pile load of the substation area, the dynamic evaluation module is configured as follows: The remaining connectable load of the target transformer area is calculated according to the following formula; ； In the formula, This indicates the remaining connectable load in the aforementioned transformer area. This indicates the current actual operating load.

4. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 2, characterized in that, The distribution network parameters also include: distribution network topology data; Specifically, when dynamically updating the remaining available load of each node in the target distribution area based on the remaining available load of the distribution area, the dynamic evaluation module is configured as follows: Based on the distribution network topology data, identify each node in the target distribution area, and obtain the historical total load of the target distribution area and the historical load of each node. Based on the historical total load and the historical load of each node, the load ratio coefficient of each node is calculated. Using the load ratio coefficient and the remaining available load in the transformer area, the allocated load for each node is calculated. Obtain the actual load of each node, and determine the remaining available load of each node based on the allocated access load of each node and the actual load of each node.

5. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 1, characterized in that, The operating status data includes: the voltage amplitude of each designated node and the reverse transmission power of each designated node; Specifically, when calculating the access metrics for each specified node based on various operational status data, the multi-constraint linkage verification module is configured as follows: For any given node, obtain the rated voltage of that given node; Calculate the voltage deviation and per-unit voltage value of any specified node based on the rated voltage and the voltage amplitude of any specified node. Based on the reverse transmission power of any specified node, calculate the reverse load rate of any specified node. Obtain the harmonic parameters and charging pile access capacity of the charging pile connected to any of the specified nodes, and calculate the harmonic current of the specified node based on the rated voltage, the harmonic parameters and the charging pile access capacity. The access index of any specified node is formed by using the voltage deviation, per-unit voltage value, reverse load rate and harmonic current of any specified node.

6. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 5, characterized in that, When calculating the voltage deviation and per-unit value of any specified node based on the rated voltage and the voltage amplitude of any specified node, the multi-constraint linkage verification module is configured as follows: The ratio between the voltage amplitude of any specified node and the rated voltage is taken as the voltage per unit value; Based on the rated voltage and the voltage amplitude of any specified node, the voltage deviation of any specified node is calculated according to the following formula; ； In the formula, This represents the voltage deviation at any of the specified nodes. This represents the voltage amplitude of any specified node. This represents the rated voltage of any of the specified nodes.

7. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 6, characterized in that, When the reverse load rate of any specified node is calculated based on the reverse transmission power of any specified node, the multi-constraint linkage verification module is configured as follows: Obtain the actual total operating load of the target transformer area before simulated access; Based on the actual total operating load and the reverse transmission power of any designated node, the reverse load rate of any designated node is calculated using the following formula. ； This represents the reverse load rate of any specified node. This represents the reverse transmission power of any of the specified nodes. This indicates the actual total operating load.

8. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 1, characterized in that, When the multi-constraint verification results of the candidate charging pile planning scheme are obtained based on various access indicators, the multi-constraint linkage verification module is configured as follows: Obtain the indicator constraint parameters for each specified node; For any given node, determine whether the voltage deviation, per-unit voltage, reverse load rate, and harmonic current of the given node all meet the index constraint parameters of the given node. If yes, then the verification result of the charging pile access planning scheme of any designated node in the candidate charging pile planning scheme is determined to be feasible; otherwise, the verification result of the charging pile access planning scheme of any designated node in the candidate charging pile planning scheme is determined to be infeasible. After all designated nodes have been traversed, the verification results of the charging pile access planning scheme of each designated node are used to form the multi-constraint verification result. Accordingly, when updating the candidate planning scheme for charging piles based on the multi-constraint verification results, the intelligent planning module is configured as follows: Based on the results of the multi-constraint verification, the nodes that are deemed infeasible for access in the charging pile access planning scheme are identified as nodes to be adjusted. A single-parameter iterative trial method is used to adjust the charging pile access capacity corresponding to each node to be adjusted, so as to obtain the updated charging pile candidate planning scheme after adjustment.

9. The dynamic assessment and intelligent planning system for the carrying capacity of charging piles in a power distribution network area according to claim 1, characterized in that, The historical data of the power distribution network also includes: historical survey information and historical planning schemes. The intelligent auxiliary model for scheme compilation is trained based on historical survey information, historical planning schemes, historical carrying capacity analysis results, multi-constraint verification results of historical planning schemes, and the corresponding operating status data of each node.

10. A method for dynamic evaluation and intelligent planning of the carrying capacity of charging piles in a power distribution network area, characterized in that, include: Obtain charging pile assessment and planning data, which includes distribution network parameters, load data, and historical distribution network data; Based on load data and distribution network parameters, the maximum load capacity of charging piles that can be connected to the target distribution area in the distribution network is calculated. Based on historical data of the distribution network, the load of the target distribution area is predicted. According to the load prediction data and the maximum load capacity of charging piles that can be connected to the distribution area, the remaining load capacity of each node in the target distribution area is dynamically updated. Based on the remaining load capacity of each node, a charging pile hierarchical access suggestion is output for each node. Obtain candidate planning schemes for charging piles; Based on the candidate planning schemes for charging piles, a simulation of the charging pile access area is conducted to obtain the operating status data of each specified node in the target area after the charging piles are connected to the target area. Based on the various operating status data, the access indicators of each specified node are calculated, and based on the access indicators, the multi-constraint verification results of the candidate planning scheme for charging piles are obtained. The access indicators of any specified node include the voltage deviation, reverse load rate, voltage per unit value and harmonic current of that specified node. Based on the results of the multi-constraint verification, the candidate planning scheme for charging piles is updated, and the charging pile access area is simulated again based on the updated candidate planning scheme until the planning convergence condition is met, and the optimal planning scheme for charging piles is obtained. Based on the charging pile access carrying capacity analysis results and the optimal charging pile planning scheme, as well as the multi-constraint verification results and the corresponding operation status data of each specified node corresponding to the optimal charging pile planning scheme, and using the pre-built scheme to intelligently assist in compiling a large model, the optimal carrying capacity improvement scheme for the target area is generated. The charging pile access carrying capacity analysis results include the charging pile hierarchical access suggestions for each node. The results of the charging pile access load capacity analysis, the optimal load capacity improvement scheme, the optimal charging pile planning scheme, and the multi-constraint verification results corresponding to the optimal charging pile planning scheme are visualized.

Images