Multi-port flexible scheduling method and system for electric vehicle charging pile

Abstract

The invention relates to the technical field of charging piles, and provides an electric vehicle charging pile multi-port flexible scheduling method and system, and the method comprises the steps: obtaining charging demand data of charging pile ports, carrying out the feature extraction of the charging demand data, obtaining a port priority sequence, and carrying out the dynamic hierarchical clustering, after the port scheduling cooperation parameter and the port scheduling compensation parameter are obtained, carrying out adaptive adjustment on a preset port scheduling strategy to obtain a port scheduling scheme; and dynamically adjusting the port priority sequence according to the port scheduling scheme, generating a flexible scheduling scheme, and performing dynamic scheduling control on the charging pile port based on the flexible scheduling scheme. The port scheduling scheme is optimized through the port scheduling cooperation parameters and the port scheduling compensation parameters, generation of the flexible scheduling scheme is achieved, high flexibility and resource utilization efficiency are shown in the actual scheduling process, and the problems that in the actual use process, flexibility is insufficient, and the response speed is low are solved.

Description

Technical Field

[0001] The present application relates to the technical field of charging piles, and in particular to a multi-port flexible scheduling method and system for electric vehicle charging piles. Background Art

[0002] With the popularity of electric vehicles, charging piles, as an important supporting infrastructure for electric vehicles, are in increasing demand. However, the utilization efficiency of charging pile resources is still one of the main factors restricting the performance of electric vehicle charging networks. Especially for multi-port charging piles, how to achieve efficient port scheduling under limited resources has become a key issue that the industry needs to solve urgently. Solving this problem is not only related to the charging experience of electric vehicle users, but also directly affects the revenue and management efficiency of charging pile operators.

[0003] In related technical means, in order to optimize the resource utilization efficiency of multiple ports of electric vehicle charging piles, the mainstream methods usually rely on predetermined static scheduling strategies. For example, according to historical charging data and port usage records, a usage order or priority strategy for charging ports is formulated. These methods can achieve load balancing and full utilization of resources to a certain extent through static allocation of port loads, thereby avoiding the problem of overloading a single port or idle resources.

[0004] Regarding the above technical solution, although a certain degree of port resource optimization can be achieved through the static scheduling strategy, in actual use, due to the uncertainty and real-time nature of user charging needs, static scheduling is often not flexible enough when facing dynamically changing charging needs, resulting in uneven resource allocation or insufficient response speed. Summary of the invention

[0005] In order to improve the problems of insufficient flexibility and slow response speed in actual use, the present application provides a multi-port flexible scheduling method and system for electric vehicle charging piles.

[0006] The present invention provides a multi-port flexible scheduling method for an electric vehicle charging pile, including: obtaining charging demand data of the charging pile ports, extracting features from the charging demand data to obtain a charging power demand feature set and a charging duration demand feature set; generating a port load balancing map based on the charging power demand feature set, performing weighted correlation calculation on the port load balancing map and the charging duration demand feature set to obtain a port priority sequence; performing dynamic hierarchical clustering on the port priority sequence to obtain a high-priority port group and a low-priority port group, generating a port scheduling mapping matrix according to the high-priority port group and the low-priority port group; performing port matching analysis on the port scheduling mapping matrix to obtain port scheduling cooperation parameters and port scheduling compensation parameters, adaptively adjusting a preset port scheduling strategy by using the port scheduling cooperation parameters and the port scheduling compensation parameters to obtain a port scheduling plan; dynamically adjusting the port priority sequence according to the port scheduling plan to generate a flexible scheduling plan, and performing dynamic scheduling control on the charging pile ports based on the flexible scheduling plan.

[0007] As a preferred solution, the step of obtaining charging demand data of the charging pile ports, extracting features from the charging demand data to obtain a charging power demand feature set and a charging duration demand feature set includes: obtaining charging demand data of the charging pile ports, where the charging demand data includes historical charging record data and current charging status data; performing time series analysis on the historical charging record data to obtain charging power change trend data and charging duration distribution data, constructing a charging demand prediction mapping according to the charging power change trend data and the charging duration distribution data, and performing mapping transformation on the current charging status data by using the charging demand prediction mapping to obtain short-term charging power demand data and short-term charging duration demand data; performing non-linear fitting calculation on the short-term charging power demand data to obtain a power demand stability parameter, performing discrete clustering processing on the short-term charging duration demand data to obtain a duration demand grouping index, and performing cross-matching by using the power demand stability parameter and the duration demand grouping index to obtain port transient load data and port continuous load data; extracting features from the port transient load data to obtain transient power demand features and transient duration demand features, extracting features from the port continuous load data to obtain continuous power demand features and continuous duration demand features; generating a charging power demand feature set based on the transient power demand features and the continuous power demand features, and generating a charging duration demand feature set based on the transient duration demand features and the continuous duration demand features.

[0008] As a preferred solution, the steps of generating a port load balancing map based on the charging power demand feature set, and performing weighted correlation calculation on the port load balancing map and the charging duration demand feature set to obtain a port priority sequence include: constructing a port power mapping matrix based on the charging power demand feature set, and constructing a port duration mapping matrix based on the charging duration demand feature set, performing topological aggregation processing on the port power mapping matrix to obtain a port load association graph, performing time window decomposition on the port duration mapping matrix to obtain a port charging duration distribution map; constructing a port load balancing map based on the port load association graph and the port charging duration distribution map, performing port load trend analysis on the port load balancing map to obtain a port load trend index, and performing weighted correlation calculation on the port load trend index and the charging duration demand feature set to obtain a port demand distribution parameter and a port load stability parameter; performing sorting calculation on the port demand distribution parameter to obtain a port demand priority index, performing hierarchical clustering on the port load stability parameter to obtain a port load adaptability index, and performing weighted fusion based on the port demand priority index and the port load adaptability index to obtain a port priority sequence.

[0009] As a preferred solution, the steps of performing dynamic hierarchical clustering on the port priority sequence to obtain a high-priority port group and a low-priority port group, and generating a port scheduling mapping matrix according to the high-priority port group and the low-priority port group include: using the port priority sequence to construct a port priority clustering graph, performing dynamic hierarchical calculation on the port priority clustering graph to obtain a high-priority port group and a low-priority port group; performing load balancing calculation on the high-priority port group to obtain a high-priority port charging stability parameter and a high-priority port charging demand adaptability parameter, performing topological optimization on the low-priority port group to obtain a low-priority port charging compensation factor and a low-priority port charging load deviation parameter; performing balanced matching on the high-priority port charging stability parameter and the low-priority port charging compensation factor to obtain a port matching fitness matrix, performing mapping calculation on the high-priority port charging demand adaptability parameter and the low-priority port charging load deviation parameter to obtain a port scheduling adaptation matrix; performing fusion calculation on the port matching fitness matrix and the port scheduling adaptation matrix to obtain a port scheduling mapping matrix.

[0010] As a preferred solution, the steps of constructing a port priority clustering graph using the port priority sequence and performing dynamic hierarchical calculation on the port priority clustering graph to obtain a high-priority port group and a low-priority port group include: performing weight analysis on each port using the port priority sequence to obtain a port load weight parameter, and constructing a port priority clustering graph based on the port load weight parameter; classifying the port priorities of the port priority clustering graph through graph structure analysis, taking the ports in the port priority clustering graph that are higher than the preset load requirements and stability requirements as the high-priority port group, and taking the ports in the port priority clustering graph that are lower than the preset load requirements and stability requirements as the low-priority port group.

[0011] As a preferred solution, the steps of performing port matching analysis on the port scheduling mapping matrix to obtain port scheduling coordination parameters and port scheduling compensation parameters, and adaptively adjusting a preset port scheduling strategy using the port scheduling coordination parameters and the port scheduling compensation parameters to obtain a port scheduling scheme include: performing port matching analysis on the port scheduling mapping matrix to obtain port scheduling coordination parameters and port scheduling compensation parameters, and performing port load prediction calculation using the port scheduling coordination parameters to obtain a port load balancing index and a port power adjustment factor; adaptively adjusting the preset port scheduling strategy using the port load balancing index and the port scheduling compensation parameters to obtain a port scheduling optimization matrix; and dynamically correcting the port scheduling optimization matrix according to the port power adjustment factor to obtain a port scheduling scheme.

[0012] As a preferred solution, the steps of dynamically adjusting the port priority sequence according to the port scheduling scheme to generate a flexible scheduling scheme and performing dynamic scheduling control on the charging pile ports based on the flexible scheduling scheme include: performing port status feedback analysis on the port scheduling scheme to obtain port real-time load parameters and a port dynamic adjustment factor, adaptively correcting the port priority sequence using the port real-time load parameters to obtain a corrected port priority index; performing non-linear conversion on the corrected port priority index using the port dynamic adjustment factor to obtain a port flexible scheduling matrix, performing scheduling optimization calculation on the port flexible scheduling matrix to obtain a flexible scheduling scheme, and performing dynamic scheduling control on the charging pile ports based on the flexible scheduling scheme.

[0013] The present application also provides a multi-port flexible scheduling system for an electric vehicle charging pile, including: an acquisition module, configured to acquire the charging demand data of the charging pile ports, extract features from the charging demand data to obtain a charging power demand feature set and a charging duration demand feature set; a calculation module, configured to generate a port load balancing map based on the charging power demand feature set, perform weighted association calculation on the port load balancing map and the charging duration demand feature set to obtain a port priority sequence; a generation module, configured to perform dynamic hierarchical clustering on the port priority sequence to obtain a high-priority port group and a low-priority port group, and generate a port scheduling mapping matrix according to the high-priority port group and the low-priority port group; an adjustment module, configured to perform port matching analysis on the port scheduling mapping matrix to obtain port scheduling cooperation parameters and port scheduling compensation parameters, and adaptively adjust a preset port scheduling strategy by using the port scheduling cooperation parameters and the port scheduling compensation parameters to obtain a port scheduling plan; a control module, configured to dynamically adjust the port priority sequence according to the port scheduling plan to generate a flexible scheduling plan, and perform dynamic scheduling control on the charging pile ports based on the flexible scheduling plan.

[0014] Compared with the prior art, the present application has the following beneficial effects: high flexibility and fast response speed. By acquiring the charging demand data of the charging pile ports and extracting features, a charging power demand feature set and a charging duration demand feature set are generated, which can comprehensively grasp the dynamic demand characteristics of the charging pile ports. Based on these features, a port load balancing map and a port priority sequence are generated, realizing the balance analysis of charging demand and port load. By generating a high-priority port group and a port scheduling mapping matrix through dynamic hierarchical clustering, the demand can be quickly matched with the port resources, and the port scheduling plan can be optimized through the port scheduling cooperation parameters and the port scheduling compensation parameters to generate a flexible scheduling plan, showing high flexibility and resource utilization efficiency in the actual scheduling process, and improving the problem of insufficient flexibility and slow response speed in the actual use process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] The structures, proportions, sizes, etc. shown in the drawings of this specification are only used to cooperate with the content disclosed in the specification for those familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention. Therefore, they do not have substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0017] Figure 1 is a schematic flowchart of a multi-port flexible scheduling method for an electric vehicle charging pile provided by an embodiment of the present invention; Figure 2 is a schematic block diagram of the structure of a multi-port flexible scheduling system for an electric vehicle charging pile provided by an embodiment of the present invention.

[0018] Description of reference numerals: 10. Multi-port flexible scheduling system for electric vehicle charging piles; 11. Acquisition module; 12. Calculation module; 13. Generation module; 14. Adjustment module; 15. Control module. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] The flowcharts shown in the drawings are only illustrative examples, and do not necessarily include all contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may be changed according to the actual situation.

[0021] It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0022] It should be further understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0023] Next, the technical solutions of the present invention will be further described in conjunction with the drawings and through specific implementation manners.

[0024] Example 1: As Figure 1 shown, this application provides a multi-port flexible scheduling method for electric vehicle charging piles, including steps S100 to S500.

[0025] Step S100: Obtain the charging demand data of the charging pile ports, extract the features of the charging demand data, and obtain the charging power demand feature set and the charging duration demand feature set.

[0026] In this step, obtaining the charging demand data of the charging pile ports is mainly achieved by real-time collecting the operation data of the charging equipment and the charging reservation data uploaded by users. Specifically, information such as the collected current, voltage, charging status, and user reservation duration is used as input, and a feature extraction algorithm is adopted to perform multi-dimensional characteristic analysis on the data, generating a charging power demand feature set and a charging duration demand feature set that can characterize the charging demand.

[0027] For example, through feature extraction, the charging power demand feature set may include the charging power change trend in different time periods, while the charging duration demand feature set can reflect the expected charging time of each port and user reservation preferences, etc.

[0028] Step S200: Generate a port load balancing map based on the charging power demand feature set, perform weighted correlation calculation on the port load balancing map and the charging duration demand feature set, and obtain a port priority sequence.

[0029] In this step, generating the port load balancing map is achieved by constructing a mathematical model. According to the load levels of different ports in the charging power demand feature set, the load conditions of each port are visualized as a matrix representation. Specifically, perform weighted correlation calculation on the port load balancing map and the charging duration demand feature set to consider the comprehensive influence of charging power and duration in scheduling, and finally generate a port priority sequence to identify the importance level of the ports.

[0030] For example, when a port has both a high load capacity and a short expected charging duration at the same time, its priority will be automatically increased and thus be assigned to the front of the priority sequence.

[0031] Step S300: Perform dynamic hierarchical clustering on the port priority sequence to obtain a high-priority port group and a low-priority port group, and generate a port scheduling mapping matrix according to the high-priority port group and the low-priority port group.

[0032] In this step, by performing dynamic hierarchical clustering on the port priority sequence, ports can be divided into high-priority port groups and low-priority port groups based on the priority relationship and load characteristics between ports. Specifically, using the hierarchical clustering algorithm, ports with similar priority characteristics are grouped, and the port grouping strategy is optimized in real time by combining the dynamic adjustment algorithm with the load changes to adapt to the current charging demand. Subsequently, a port scheduling mapping matrix is generated based on the high-priority port group and the low-priority port group. This matrix synthesizes the rapid response ability of high-priority ports and the resource supplementarity of low-priority ports, thus providing a more accurate reference basis for subsequent task scheduling.

[0033] For example, in a certain actual scenario, through hierarchical clustering analysis, it is found that Port A and Port B are classified into the high-priority port group due to their high priority and load adaptability, while Port C and Port D are classified into the low-priority port group due to their lower response ability. In the generated port scheduling mapping matrix, Port A and Port B are assigned higher task allocation weights to handle emergency charging demands, while the task weights of Port C and Port D are appropriately reduced to share non-emergency tasks, thereby improving the resource utilization efficiency and response ability of the entire charging network.

[0034] Step S400: Conduct port matching analysis on the port scheduling mapping matrix to obtain port scheduling coordination parameters and port scheduling compensation parameters, and adaptively adjust the preset port scheduling strategy using the port scheduling coordination parameters and port scheduling compensation parameters to obtain a port scheduling plan.

[0035] In this step, the port matching analysis uses an optimization algorithm. According to the matching results in the port scheduling mapping matrix, the port scheduling coordination parameters are calculated to optimize the overall port usage efficiency, and the port scheduling compensation parameters are calculated to balance the imbalance problem caused by load differences. Specifically, the preset port scheduling strategy is optimized and adjusted through these parameters to ensure the adaptability and operability of the scheduling plan.

[0036] For example, when some ports are in a long-term low-load state, the port scheduling compensation parameters will increase their load by reallocating tasks, thereby improving the overall resource utilization rate.

[0037] Step S500: Dynamically adjust the port priority sequence according to the port scheduling plan to generate a flexible scheduling plan, and perform dynamic scheduling control on the charging pile ports based on the flexible scheduling plan.

[0038] In this step, the port priority sequence is dynamically adjusted to update the port scheduling scheme according to the real-time changes of the charging demand data, generating a flexible scheduling scheme to ensure that the scheduling strategy always matches the actual demand. Specifically, the charging pile ports are dynamically scheduled and controlled through the flexible scheduling scheme to adjust the working status of the ports in real time, improving the scheduling efficiency.

[0039] For example, in actual operation, when a new emergency charging demand occurs, the flexible scheduling scheme can quickly adjust the original port priority and allocate high-priority ports to users with emergency demands.

[0040] In this embodiment, by obtaining the charging demand data of the charging pile ports and extracting the features of the charging demand data, a charging power demand feature set and a charging duration demand feature set are generated. Subsequently, a port load balancing map is generated based on the charging power demand feature set. Through weighted correlation calculation of the port load balancing map and the charging duration demand feature set, a port priority sequence is obtained. Then, dynamic hierarchical clustering is performed on the port priority sequence, which is divided into a high-priority port group and a low-priority port group, and a port scheduling mapping matrix is generated according to the high-priority port group. Then, port matching analysis is performed on the port scheduling mapping matrix to obtain port scheduling cooperation parameters and port scheduling compensation parameters, and these parameters are used to adaptively adjust the preset port scheduling strategy, thereby forming a port scheduling scheme. Finally, the port priority sequence is dynamically adjusted according to the port scheduling scheme to generate a flexible scheduling scheme, and dynamic scheduling control is implemented on the charging pile ports based on the flexible scheduling scheme. The flexible scheduling of the charging pile ports is effectively realized, thus significantly improving the utilization efficiency of the charging pile port resources and avoiding the load imbalance problem caused by static scheduling. At the same time, it can adapt to the dynamic changes of user charging demands. By adaptively adjusting the port scheduling strategy, the scheduling flexibility and reliability of the system under the condition of uncertainty of charging demand data are improved, and the problems of insufficient flexibility and slow response speed in the actual use process are improved.

[0041] Embodiment 2: In step S100, the charging demand data of the charging pile ports is obtained, where the charging demand data includes historical charging record data and current charging status data.

[0042] By collecting and fusing historical charging record data and current charging status data, the usage characteristics of the charging pile ports over time and the real-time charging status can be comprehensively reflected. Specifically, the historical charging record data is obtained by calling the database interface of the charging pile background, including information such as the start and end times of user charging, the power change curve, and the charging duration. The current charging status data is collected by acquiring the real-time operating parameters of the charging pile ports, including real-time voltage, current, port occupancy status, etc., thus providing comprehensive basic data support for subsequent feature analysis.

[0043] For example, in the historical charging records of a certain charging pile group, the charging power and duration data for each time period of each day are recorded, while the current charging status data real-time displays information such as the current charging power and the estimated completion duration of each port. Through fusion analysis, these data can accurately reflect the dynamic charging demand.

[0044] Perform time series analysis on the historical charging record data to obtain the charging power change trend data and the charging duration distribution data. Based on the charging power change trend data and the charging duration distribution data, construct a charging demand prediction mapping. Use the charging demand prediction mapping to perform mapping transformation on the current charging status data to obtain the short-term charging power demand data and the short-term charging duration demand data.

[0045] Through time series analysis of the historical charging record data, the change law of the charging power in different time periods and the statistical distribution characteristics of the charging duration can be grasped. Specifically, use the time series decomposition algorithm to extract the trend component, seasonal component, and random disturbance component in the data, and construct a charging demand prediction mapping that can reflect future short-term charging demands. Subsequently, map the current charging status data into the prediction model for data matching and transformation to generate the short-term charging power demand data and the short-term charging duration demand data, providing an accurate charging demand basis for the subsequent steps.

[0046] For example, through time series analysis, it is found that the power demand of the charging piles in a certain area increases significantly during the evening peak period (17:00 - 20:00), and the user charging duration mainly concentrates between 30 and 60 minutes. Through the prediction mapping, the short-term power demand and short-term charging duration data during the evening peak can be accurately obtained.

[0047] Perform non-linear fitting calculation on the short-term charging power demand data to obtain the power demand stability parameter, perform discrete clustering processing on the short-term charging duration demand data to obtain the duration demand grouping index, and use the power demand stability parameter and the duration demand grouping index for cross-matching to obtain the port transient load data and the port continuous load data.

[0048] By performing non - linear fitting calculations on the short - term charging power demand data, polynomial fitting, exponential fitting, or other non - linear algorithms can be used to model and analyze the data, extract the stability change characteristics of the charging power demand in a short period, and generate power demand stability parameters. Specifically, by curve - fitting the short - term charging power data for each time period, the amplitude and trend of power changes can be described, providing a stability reference for subsequent matching. At the same time, by performing discrete clustering on the short - term charging duration demand data, the duration demand data is divided into multiple groups according to similarity, generating a duration demand grouping index. Cross - matching using the power demand stability parameter and the duration demand grouping index can combine the power demand stability with the duration demand classification data to generate more refined port transient load data and port continuous load data.

[0049] For example, in a charging scenario, the stability parameter obtained after fitting the short - term charging power demand data of a certain port is low fluctuation, and its short - term charging duration demand data is clustered into the short - duration demand group. When the power stability parameter is cross - matched with the duration grouping index, the generated transient load data can reflect the short - term demands that the port needs to respond quickly to, while the continuous load data indicates the long - term resource utilization tendency of the port.

[0050] Feature extraction is performed on the port transient load data to obtain transient power demand features and transient duration demand features, and feature extraction is performed on the port continuous load data to obtain continuous power demand features and continuous duration demand features.

[0051] By performing feature extraction on the port transient load data and the port continuous load data, transient power demand features and transient duration demand features, as well as continuous power demand features and continuous duration demand features, can be obtained respectively. Specifically, the feature extraction of transient load data uses short - term trend analysis techniques to capture the rapid response characteristics of power demand and their corresponding duration characteristics in a short period; while the feature extraction of continuous load data uses long - term averaging and trend - fitting methods to describe the regularity of power and duration demands in a stable state.

[0052] For example, after feature extraction of the transient load data of a certain port, the transient power demand feature shows high power fluctuation, and the transient duration demand feature shows a shorter duration distribution; for the continuous load data of the same port, its continuous power demand feature shows stable average power output, and the continuous duration demand feature indicates that the port is more suitable for long - duration charging tasks.

[0053] Based on the transient power demand features and continuous power demand features, a charging power demand feature set is generated, and based on the transient duration demand features and continuous duration demand features, a charging duration demand feature set is generated.

[0054] By fusing and analyzing the transient power demand characteristics and the continuous power demand characteristics, a set of charging power demand characteristics is generated. At the same time, the transient duration demand characteristics and the continuous duration demand characteristics are integrated to form a set of charging duration demand characteristics. Specifically, the set of charging power demand characteristics synthesizes the variation characteristics of the port power demand in the short-term and long-term ranges, providing a comprehensive reference for power distribution; while the set of charging duration demand characteristics integrates the charging duration demands of the port in different time dimensions, providing an accurate duration basis for the scheduling strategy.

[0055] For example, after fusing the transient power demand characteristics and the continuous power demand characteristics of a certain port, the set of charging power demand characteristics shows the high sensitivity of the port to power changes in the short term and the stable output ability of the long-term power; while its set of charging duration demand characteristics comprehensively reflects the user's demand preferences for short-term and long-term charging, facilitating the dynamic optimization of subsequent scheduling strategies.

[0056] In step S200, a port power mapping matrix is constructed based on the set of charging power demand characteristics, and a port duration mapping matrix is constructed based on the set of charging duration demand characteristics. The port power mapping matrix is topologically aggregated to obtain a port load association graph, and the port duration mapping matrix is decomposed by time window to obtain a port charging duration distribution map.

[0057] By constructing the port power mapping matrix, the data in the set of charging power demand characteristics is associated with the specific distribution of each port, realizing the mapping of charging demand and the actual port power capacity. Specifically, using the matrix modeling method, the power demand of each port is mapped to the row and column values of a two-dimensional matrix, reflecting the correlation between power demand and the port. Similarly, a port duration mapping matrix is constructed. Through the decomposition and analysis of the set of charging duration demand characteristics, the demand duration characteristics are associated with each port. Subsequently, the port power mapping matrix is topologically aggregated. Based on the power complementarity between adjacent ports, a connection graph structure is established, thus forming a port load association graph. For the port duration mapping matrix, through time window decomposition, the demand duration characteristics in different time periods are decomposed into multiple time segments, generating a port charging duration distribution map, and clarifying the duration load characteristics of each port in different time slices.

[0058] For example, in a certain charging scenario, the values in a port power mapping matrix reflect the power demand of a certain port in a specific time period. After topological aggregation, the port load association graph shows the complementarity between the high-power demand port and the adjacent low-power demand port. At the same time, the port duration mapping matrix is decomposed by time window, dividing a day into multiple time slices, and presenting the duration load levels of each port in each time slice in the port charging duration distribution map.

[0059] Construct a port load balancing map based on the port load association map and the port charging duration distribution map, perform port load trend analysis on the port load balancing map to obtain port load trend indicators, and perform weighted association calculation on the port load trend indicators and the charging duration demand feature set to obtain port demand distribution parameters and port load stability parameters.

[0060] By fusing and analyzing the port load association map and the port charging duration distribution map, construct a port load balancing map to comprehensively describe the load distribution characteristics of the ports. Specifically, use the load balancing map to analyze the load change trend of the ports, extract port load trend indicators reflecting the load change law, and perform weighted association calculation in combination with the charging duration demand feature set, so as to obtain port demand distribution parameters and port load stability parameters. The port demand distribution parameters mainly describe the load demand distribution of the ports in space, while the port load stability parameters reflect the stability of the ports in the changes of power load and duration demand.

[0061] For example, in the port load balancing map, a certain port shows a law of gradually decreasing load trend at different times of a day, and its load trend indicator reflects the load concentration phenomenon during the peak period. After weighted association calculation, the port demand distribution parameters reveal the demand distribution characteristics of a specific area, while the port load stability parameters indicate the load stable state of high-load ports during long-term operation.

[0062] Perform sorting calculation on the port demand distribution parameters to obtain the port demand priority index, perform hierarchical clustering on the port load stability parameters to obtain the port load adaptability index, and perform weighted fusion based on the port demand priority index and the port load adaptability index to obtain the port priority sequence.

[0063] By performing sorting calculation on the port demand distribution parameters, the importance of port demands can be intuitively obtained to generate the port demand priority index; at the same time, by performing hierarchical clustering on the port load stability parameters, the ports are divided into different levels according to the similarity of the parameters to obtain the port load adaptability index. Subsequently, by weighted fusion of the port demand priority index and the port load adaptability index, combined with the urgency and adaptability of the demands, a port priority sequence is generated to guide the formulation of subsequent scheduling strategies.

[0064] For example, in a certain calculation scenario, a port with high demand and good load adaptability is given the highest priority, while another port with medium demand but poor adaptability is assigned to the low-priority sequence, thus providing a clear allocation basis for the scheduling strategy.

[0065] In step S300, use the port priority sequence to construct a port priority clustering map, and perform dynamic hierarchical calculation on the port priority clustering map to obtain a high-priority port group and a low-priority port group.

[0066] By constructing a port priority clustering graph using the port priority sequence, the priorities of each port can be visually expressed through topological analysis methods, and the priority relationships between ports can be clarified. Specifically, based on the sorting results in the port priority sequence, a clustering algorithm is used to group the ports according to their priorities, generating a clustering graph that includes the division of high-priority and low-priority ports. Subsequently, through dynamic hierarchical calculation, on the basis of considering the dynamic changes in port load and resource distribution, the hierarchical rules are further optimized to generate high-priority and low-priority port groups that meet the current requirements.

[0067] For example, in a certain charging network, the priority sequence shows that ports A and B have light loads and fast responses, and after clustering analysis, they are classified into the high-priority port group, while ports C and D are classified into the low-priority port group due to their high loads.

[0068] Perform load balancing calculations on the high-priority port group to obtain the charging stability parameter and charging demand adaptability parameter of the high-priority ports, and perform topological optimization on the low-priority port group to obtain the charging compensation factor and charging load deviation parameter of the low-priority ports.

[0069] Through the load balancing calculation of the high-priority port group, the load distribution and response characteristics of the high-priority port group during the charging process can be analyzed, further quantifying the charging stability of the high-priority ports and their ability to adapt to different demands, and generating the charging stability parameter and charging demand adaptability parameter of the high-priority ports. For the low-priority port group, through topological optimization, based on the load distribution and power complementarity between ports, the charging compensation factor of the low-priority ports and the load deviation characteristics are calculated, providing data support for subsequent load regulation.

[0070] For example, ports E and F belong to the high-priority group, and the load balancing calculation results show that they have high charging stability and strong adaptability; while for port G in the low-priority group, due to its heavy load, the compensation factor calculated by topological optimization indicates that the load deviation needs to be reduced by about 20%.

[0071] Balance and match the charging stability parameter of the high-priority ports and the charging compensation factor of the low-priority ports to obtain the port matching fitness matrix, and perform mapping calculations on the charging demand adaptability parameter of the high-priority ports and the charging load deviation parameter of the low-priority ports to obtain the port scheduling adaptation matrix.

[0072] By performing matching calculations on the charging stability parameters of high-priority ports and the charging compensation factors of low-priority ports, a port matching fitness matrix is formed, which can quantify the load balance between high-priority ports and low-priority ports. At the same time, by mapping and calculating the charging demand adaptability parameters of high-priority ports and the load deviation parameters of low-priority ports, a port scheduling adaptation matrix is generated, providing an accurate basis for scheduling mapping.

[0073] For example, in a certain charging network, the matching fitness matrix shows that the high stability of port H can compensate for the overloading phenomenon of port I, while the scheduling adaptation matrix recommends transferring urgent demands to port J with high adaptability.

[0074] The port matching fitness matrix and the port scheduling adaptation matrix are fused and calculated to obtain a port scheduling mapping matrix.

[0075] By performing fusion calculations on the port matching fitness matrix and the port scheduling adaptation matrix, the load balance matching results and the adaptability mapping results are comprehensively considered to generate a port scheduling mapping matrix. Specifically, the port scheduling mapping matrix can not only reflect the load balancing strategy between ports, but also adapt to real-time charging demands in a dynamic manner, optimizing the utilization efficiency of port resources.

[0076] For example, the results of the fusion calculation show that the tasks of high-load port K can be adjusted to port L with stronger adaptability according to the recommendations of the mapping matrix, thus achieving the optimal allocation of resources.

[0077] Among them, the steps of constructing a port priority clustering graph using the port priority sequence and performing dynamic hierarchical calculations on the port priority clustering graph to obtain high-priority port groups and low-priority port groups include: performing weight analysis on each port using the port priority sequence to obtain port load weight parameters, and constructing a port priority clustering graph based on the port load weight parameters.

[0078] Through the weight analysis in the port priority sequence, the importance indicators of each port in resource allocation can be extracted to generate functional port load weight parameters. Specifically, based on these parameters and combined with the dynamic connections between ports, a port priority clustering graph is constructed to more intuitively present the dynamic changes of priorities.

[0079] For example, the weight parameters of port M show that its power demand and duration demand are both higher than the average, so it is located in the node area with higher priority in the clustering graph.

[0080] By analyzing the port priorities of the port priority clustering graph through graph structure analysis, the ports in the port priority clustering graph that are higher than the preset load demand and stability demand are used as high-priority port groups, and the ports in the port priority clustering graph that are lower than the preset load demand and stability demand are used as low-priority port groups.

[0081] Through graph structure analysis, using the connection weights between nodes in the graph, the ports are classified according to the preset load demand and stability demand criteria, and thus divided into a high-priority port group and a low-priority port group. This step ensures the accuracy and dynamic adaptability of port priority classification.

[0082] For example, in a certain graph structure, high-priority nodes are concentrated in the port set that meets high power stability and uniform load, while low-priority nodes are distributed in the port set with overload or slow response.

[0083] In step S400, port matching analysis is performed on the port scheduling mapping matrix to obtain port scheduling cooperation parameters and port scheduling compensation parameters. The port scheduling cooperation parameters are used for port load prediction calculation to obtain the port load balance index and the port power adjustment factor.

[0084] Through the matching analysis of the port scheduling mapping matrix, considering the current load situation and future charging requirements of the ports, the port scheduling cooperation parameters and port scheduling compensation parameters are obtained. Specifically, the port scheduling cooperation parameters reflect the load cooperation ability between different ports, including the balance of task transfer between ports; the port scheduling compensation parameters are used to describe the compensation ability to adjust the load in special cases. Subsequently, the port scheduling cooperation parameters are used for load prediction calculation, and the port load change trend in the future time period is evaluated based on the prediction model to generate the port load balance index and the port power adjustment factor, where the load balance index is used to quantify the uniformity of load distribution, and the power adjustment factor represents the power amplitude to be adjusted in dynamic adjustment.

[0085] For example, in a certain charging scenario, through matching analysis, it is found that the load cooperation between port A and port B is high, and their cooperation parameters are relatively good, while port C needs to be compensated and adjusted due to concentrated load. Load prediction shows that port A will have a heavy load during the future peak period, and the corresponding load balance index is low, but the power adjustment factor suggests increasing part of the load on port B to balance its distribution.

[0086] The preset port scheduling strategy is adaptively adjusted using the port load balance index and the port scheduling compensation parameters to obtain the port scheduling optimization matrix.

[0087] By combining the port load balance index and the port scheduling compensation parameters with the existing port scheduling strategy, an adaptive adjustment algorithm is used to dynamically optimize the scheduling strategy to generate the port scheduling optimization matrix. Specifically, the port scheduling optimization matrix, while ensuring the fast response of high-priority tasks, balances the load pressure between ports through the compensation parameters and improves the fairness and flexibility of the overall scheduling in combination with the load balance index.

[0088] For example, in practical applications, the scheduling optimization matrix reduces the task allocation for the high-load port D, while increasing a certain amount of load allocation for ports E and F with higher compensation parameters, significantly improving the load balancing effect of the overall system.

[0089] Dynamically correct the port scheduling optimization matrix according to the port power adjustment factor to obtain the port scheduling plan.

[0090] By analyzing the port power adjustment factor, further dynamically correct the port scheduling optimization matrix, and combine the real-time charging demand and power adjustment demand to formulate an accurate port scheduling plan. Specifically, the corrected port scheduling plan can not only meet the rapid response of emergency tasks, but also give full play to the utilization efficiency of port resources, ensuring the scientificity and flexibility of scheduling.

[0091] For example, in a scenario of load fluctuation, it is found through dynamic correction that the port power adjustment factor of port G requires reducing part of the charging power, and reasonably allocating the excess tasks to ports H and I, thus ensuring the rapid response to real-time demands and global load balancing.

[0092] In step S500, conduct port status feedback analysis on the port scheduling plan to obtain the port real-time load parameters and port dynamic adjustment factors, and adaptively correct the port priority sequence using the port real-time load parameters to obtain the corrected port priority index.

[0093] Through the port status feedback analysis of the port scheduling plan, the current charging load situation and resource utilization efficiency of the port can be monitored in real time, so as to extract the port real-time load parameters to quantify the port load level. At the same time, according to the port real-time load parameters, use an algorithm based on dynamic priority adjustment to optimize and correct the original port priority sequence, ensuring that the port priority setting can timely reflect the actual demand and current load status, thus generating the corrected port priority index. Specifically, the port real-time load parameters are calculated by collecting real-time data such as the current, voltage, and charging task progress, and the port dynamic adjustment factor is dynamically generated based on the load fluctuation range and demand change speed, and is used to correct the weight allocation of the priority sequence.

[0094] For example, in a certain practical application scenario, due to the increase in load pressure on port A, its real-time load parameter rises significantly. The system adaptively corrects the port priority sequence according to this data, reduces the priority of port A, and at the same time increases the priority of port B (with lower load) to ensure the overall efficiency of the system.

[0095] The non - linear transformation is performed on the corrected port priority index using the port dynamic adjustment factor to obtain the port flexible scheduling matrix. The scheduling optimization calculation is carried out on the port flexible scheduling matrix to obtain the flexible scheduling scheme, and the dynamic scheduling control of the charging pile port is carried out based on the flexible scheduling scheme.

[0096] By using the port dynamic adjustment factor to perform non - linear transformation on the corrected port priority index, the weight distribution between priority indexes can be adjusted more flexibly, generating a port flexible scheduling matrix that comprehensively reflects the real - time demand and load characteristics of the port. Specifically, the non - linear transformation combines multiple parameters such as load weight, priority correction factor, and real - time change of demand, optimizing the elastic characteristics of the priority distribution. Subsequently, the scheduling optimization calculation is carried out on the port flexible scheduling matrix, and the scheduling strategy is precisely adjusted through the dynamic optimization algorithm to generate the flexible scheduling scheme. The flexible scheduling scheme not only efficiently utilizes port resources but also takes into account the real - time nature of charging demand and response flexibility, and based on this scheme, the dynamic scheduling control of the charging pile port is implemented to achieve the optimized operation of the charging pile network.

[0097] For example, in the real - time scheduling scenario, the flexible scheduling matrix shows that port C has a high response ability and a light load. Therefore, in the flexible scheduling scheme, it is preferentially arranged to handle sudden charging demands, while port D with a high load is dynamically assigned low - priority tasks, thus ensuring the load balance and response efficiency of the entire system.

[0098] In this embodiment, by collecting and analyzing the charging demand data of the charging pile ports in detail, integrating the historical charging record data and the current charging status data, and using time series analysis and feature extraction technologies, rich feature data including short-term charging power demand data and short-term charging duration demand data are obtained. Further, through calculation methods such as non-linear fitting, discrete clustering, and cross-matching, transient load data and continuous load data of the ports are generated, and transient power demand features, transient duration demand features, continuous power demand features, and continuous duration demand features are extracted to construct a charging power demand feature set and a charging duration demand feature set. Based on these feature data, a port power mapping matrix and a port duration mapping matrix are constructed, and then topological aggregation and time window decomposition are performed to generate a port load association graph and a port charging duration distribution graph. Finally, a port load balancing map is constructed and load trend and stability parameters are extracted through multi-dimensional analysis. Combining the port demand distribution parameters and the load adaptability parameters, the dynamic calculation of the port priority sequence is completed. Subsequently, a priority clustering graph is generated using the port priority sequence, and through dynamic hierarchical and load balancing calculations, the ports are divided into high-priority and low-priority groups, and a port scheduling mapping matrix is generated through matching and mapping. In the scheduling stage, through port load prediction and adaptive adjustment strategies, the scheduling strategy is optimized to generate a port scheduling optimization matrix and a final port scheduling plan. In the feedback analysis link, the port priority index is corrected using real-time data, and the final dynamic scheduling control is performed using a flexible scheduling matrix, realizing the efficient utilization of charging pile port resources and the flexibility of real-time scheduling, thereby significantly improving the overall system performance and the user charging experience.

[0099] Embodiment 3: As Figure 2 shown, the present application also provides a multi-port flexible scheduling system 10 for an electric vehicle charging pile, including an acquisition module 11, a calculation module 12, a generation module 13, an adjustment module 14, and a control module 15.

[0100] The acquisition module 11 is configured to acquire the charging demand data of the charging pile ports, extract features from the charging demand data, and obtain a charging power demand feature set and a charging duration demand feature set.

[0101] The calculation module 12 is configured to generate a port load balancing map based on the charging power demand feature set, perform weighted association calculation on the port load balancing map and the charging duration demand feature set, and obtain a port priority sequence.

[0102] The generation module 13 is configured to perform dynamic hierarchical clustering on the port priority sequence to obtain a high-priority port group and a low-priority port group, and generate a port scheduling mapping matrix according to the high-priority port group and the low-priority port group.

[0103] An adjustment module 14 is configured to perform port matching analysis on a port scheduling mapping matrix to obtain port scheduling coordination parameters and port scheduling compensation parameters, and adaptively adjust a preset port scheduling policy by using the port scheduling coordination parameters and the port scheduling compensation parameters to obtain a port scheduling scheme.

[0104] A control module 15 is configured to dynamically adjust a port priority sequence according to the port scheduling scheme to generate a flexible scheduling scheme, and perform dynamic scheduling control on a charging pile port based on the flexible scheduling scheme.

[0105] In this embodiment, through the acquisition module 11, the charging demand data of the charging pile ports is comprehensively collected and deeply analyzed. The system can extract and generate a charging power demand feature set and a charging duration demand feature set, providing rich and accurate basic data support for subsequent scheduling steps. Through the calculation module 12, a port load balancing map is generated by using the charging power demand feature set, and weighted correlation calculation is performed on it and the charging duration demand feature set to obtain a port priority sequence reflecting the priorities of each port, thus realizing the preliminary optimization of resource allocation. The generation module 13 further divides a high-priority port group and a low-priority port group through dynamic hierarchical clustering of the port priority sequence, and at the same time generates a port scheduling mapping matrix based on the high-priority port group, providing a directional guidance for accurate scheduling. The adjustment module 14 calculates port scheduling coordination parameters and port scheduling compensation parameters through port matching analysis of the port scheduling mapping matrix, and adaptively adjusts a preset port scheduling policy by using these parameters, effectively optimizing the port scheduling scheme and significantly improving the flexibility of scheduling and the scientificity of resource allocation. The control module 15 dynamically adjusts the port priority sequence according to the optimized port scheduling scheme, generates a flexible scheduling scheme, and performs dynamic scheduling control on the charging pile ports, thus comprehensively improving the system's response ability to real-time changes in charging demands. The overall solution, through a modular design concept and refined function division, fully ensures the efficient operation and real-time performance of the multi-port scheduling system, significantly improves the user charging experience, and enhances the overall operation efficiency of the charging network.

[0106] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described device and each module can refer to the corresponding processes in the foregoing Embodiment 1, and will not be elaborated herein.

[0107] The structures, proportions, sizes, etc. shown in the accompanying drawings of this specification are only used to cooperate with the content disclosed in the specification for those familiar with this technology to understand and read, and are not used to limit the conditions for the implementation of the present invention. Therefore, they do not have substantial technical significance. Any modification of the structure, change in the proportional relationship, or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0108] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-port flexible scheduling method for electric vehicle charging piles, characterized in that: include: Acquire charging demand data of the charging pile port, perform feature extraction on the charging demand data, and obtain a charging power demand feature set and a charging time demand feature set; Generate a port load balancing map based on the charging power demand feature set, and perform weighted association calculation on the port load balancing map and the charging time demand feature set to obtain a port priority sequence; Dynamically hierarchically clustering the port priority sequence to obtain a high priority port group and a low priority port group, and generating a port scheduling mapping matrix according to the high priority port group and the low priority port group; Performing port matching analysis on the port scheduling mapping matrix to obtain port scheduling coordination parameters and port scheduling compensation parameters, and adaptively adjusting a preset port scheduling strategy using the port scheduling coordination parameters and the port scheduling compensation parameters to obtain a port scheduling solution; The port priority sequence is dynamically adjusted according to the port scheduling scheme to generate a flexible scheduling scheme, and the charging pile port is dynamically scheduled and controlled based on the flexible scheduling scheme.

2. The electric vehicle charging pile multi-port flexible scheduling method according to claim 1 is characterized in that: The step of acquiring charging demand data of the charging pile port, extracting features from the charging demand data, and obtaining a charging power demand feature set and a charging time demand feature set includes: Acquire charging demand data of the charging pile port, wherein the charging demand data includes historical charging record data and current charging status data; Performing a time series analysis on the historical charging record data to obtain charging power change trend data and charging duration distribution data, constructing a charging demand prediction map according to the charging power change trend data and the charging duration distribution data, and performing a mapping transformation on the current charging state data using the charging demand prediction map to obtain short-term charging power demand data and short-term charging duration demand data; Perform nonlinear fitting calculation on the short-time charging power demand data to obtain a power demand stability parameter, perform discrete clustering processing on the short-time charging duration demand data to obtain a duration demand grouping index, and use the power demand stability parameter and the duration demand grouping index for cross-matching to obtain port transient load data and port continuous load data; Extracting features from the transient load data of the port to obtain transient power demand features and transient duration demand features, and extracting features from the continuous load data of the port to obtain continuous power demand features and continuous duration demand features; A charging power requirement feature set is generated based on the transient power requirement feature and the continuous power requirement feature, and a charging duration requirement feature set is generated based on the transient duration requirement feature and the continuous duration requirement feature.

3. The electric vehicle charging pile multi-port flexible scheduling method according to claim 1 is characterized in that: The step of generating a port load balancing map based on the charging power demand feature set, performing weighted association calculation on the port load balancing map and the charging time demand feature set to obtain a port priority sequence includes: Constructing a port power mapping matrix based on the charging power demand feature set, and constructing a port duration mapping matrix based on the charging duration demand feature set, performing topological aggregation processing on the port power mapping matrix to obtain a port load association graph, and performing time window decomposition on the port duration mapping matrix to obtain a port charging duration distribution graph; A port load balancing graph is constructed based on the port load association graph and the port charging time distribution graph, a port load trend analysis is performed on the port load balancing graph to obtain a port load trend index, and a weighted correlation calculation is performed on the port load trend index and the charging time demand feature set to obtain a port demand distribution parameter and a port load stability parameter; The port demand distribution parameters are sorted and calculated to obtain a port demand priority index, the port load stability parameters are hierarchically clustered to obtain a port load adaptability index, and weighted fusion is performed based on the port demand priority index and the port load adaptability index to obtain a port priority sequence.

4. The multi-port flexible scheduling method for electric vehicle charging piles according to claim 1 is characterized in that: The step of dynamically hierarchically clustering the port priority sequence to obtain a high priority port group and a low priority port group, and generating a port scheduling mapping matrix according to the high priority port group and the low priority port group comprises: Constructing a port priority clustering graph by using the port priority sequence, and performing dynamic hierarchical calculation on the port priority clustering graph to obtain a high priority port group and a low priority port group; Performing load balancing calculation on the high priority port group to obtain a high priority port charging stability parameter and a high priority port charging demand adaptability parameter, and performing topology optimization on the low priority port group to obtain a low priority port charging compensation factor and a low priority port charging load deviation parameter; Performing balanced matching on the charging stability parameter of the high priority port and the charging compensation factor of the low priority port to obtain a port matching fitness matrix, and performing mapping calculation on the charging demand adaptability parameter of the high priority port and the charging load deviation parameter of the low priority port to obtain a port scheduling adaptation matrix; The port matching fitness matrix and the port scheduling adaptation matrix are fused and calculated to obtain a port scheduling mapping matrix.

5. The electric vehicle charging pile multi-port flexible scheduling method according to claim 4 is characterized in that: The step of constructing a port priority clustering graph by using the port priority sequence, and performing dynamic hierarchical calculation on the port priority clustering graph to obtain a high priority port group and a low priority port group comprises: Performing weight analysis on each port using the port priority sequence to obtain a port load weight parameter, and constructing a port priority clustering graph according to the port load weight parameter; The port priorities of the port priority clustering graph are classified through graph structure analysis, and the ports in the port priority clustering graph that are higher than the preset load requirements and stability requirements are regarded as a high priority port group, and the ports in the port priority clustering graph that are lower than the preset load requirements and stability requirements are regarded as a low priority port group.

6. The electric vehicle charging pile multi-port flexible scheduling method according to claim 1, characterized in that: The step of performing port matching analysis on the port scheduling mapping matrix to obtain port scheduling coordination parameters and port scheduling compensation parameters, and adaptively adjusting a preset port scheduling strategy using the port scheduling coordination parameters and the port scheduling compensation parameters to obtain a port scheduling solution includes: Performing port matching analysis on the port scheduling mapping matrix to obtain port scheduling coordination parameters and port scheduling compensation parameters, and performing port load prediction calculation using the port scheduling coordination parameters to obtain a port load balancing index and a port power adjustment factor; Adaptively adjusting the preset port scheduling strategy using the port load balancing index and the port scheduling compensation parameter to obtain a port scheduling optimization matrix; The port scheduling optimization matrix is ​​dynamically modified according to the port power adjustment factor to obtain a port scheduling solution.

7. The electric vehicle charging pile multi-port flexible scheduling method according to claim 1, characterized in that: The step of dynamically adjusting the port priority sequence according to the port scheduling scheme, generating a flexible scheduling scheme, and dynamically scheduling and controlling the charging pile port based on the flexible scheduling scheme includes: Performing port status feedback analysis on the port scheduling scheme to obtain a port real-time load parameter and a port dynamic adjustment factor, and adaptively correcting the port priority sequence using the port real-time load parameter to obtain a corrected port priority index; The corrected port priority index is nonlinearly transformed by using the port dynamic adjustment factor to obtain a port flexible scheduling matrix, a scheduling optimization calculation is performed on the port flexible scheduling matrix to obtain a flexible scheduling scheme, and the charging pile port is dynamically scheduled and controlled based on the flexible scheduling scheme.

8. A multi-port flexible dispatching system for electric vehicle charging piles, characterized in that: include: An acquisition module is used to acquire charging demand data of a charging pile port, perform feature extraction on the charging demand data, and obtain a charging power demand feature set and a charging time demand feature set; A calculation module, configured to generate a port load balancing map based on the charging power demand feature set, and perform weighted association calculation on the port load balancing map and the charging time demand feature set to obtain a port priority sequence; A generating module, used for dynamically hierarchically clustering the port priority sequence to obtain a high priority port group and a low priority port group, and generating a port scheduling mapping matrix according to the high priority port group and the low priority port group; An adjustment module, configured to perform port matching analysis on the port scheduling mapping matrix to obtain a port scheduling coordination parameter and a port scheduling compensation parameter, and adaptively adjust a preset port scheduling strategy using the port scheduling coordination parameter and the port scheduling compensation parameter to obtain a port scheduling solution; The control module is used to dynamically adjust the port priority sequence according to the port scheduling scheme, generate a flexible scheduling scheme, and dynamically schedule and control the charging pile port based on the flexible scheduling scheme.

Images