Charging station optimization deployment method based on operation state

Abstract

The invention provides a charging station optimization deployment method based on an operation state, and the method comprises the steps: obtaining the operation data of an existing charging station, and constructing a saturation index based on the operation data; a neighborhood radius is set, an adjacent station set of each charging station is determined, a siphon intensity index is calculated based on the saturation index of each station in the adjacent station set, and competitive advantage stations are identified according to the saturation index, the siphon intensity index and the competitive condition of each charging station; operation features of all the charging stations are extracted, operation feature vectors are constructed, and clustering analysis is carried out according to the operation feature vectors to divide operation modes of the charging stations; and integrating the saturation index, the competitive advantage site identification result and the operation mode clustering result to carry out multi-dimensional evaluation, and generating a differentiated optimization deployment strategy according to a multi-dimensional evaluation result. By applying the method, station value and bottleneck can be mined from real operation feedback, and charging network planning is promoted to be transformed from static coverage to a dynamic feedback and efficiency-first refined mode.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation and energy infrastructure planning technology, and in particular to a method for optimizing the deployment of charging stations based on operational status. Background Technology

[0002] With the deepening of the global energy structure transformation, the electric vehicle (EV) industry is experiencing rapid development. Charging infrastructure, as a crucial component supporting its daily operation, directly impacts user charging experience and the popularization of EVs through its scientific planning and construction. However, current charging networks generally suffer from supply-demand mismatch and low operational efficiency: some charging stations approach or reach their service capacity limits during peak hours, while others operate at low capacity for extended periods, reflecting significant spatiotemporal fluctuations in charging demand and a structural imbalance in planning and layout.

[0003] Traditional research on optimal site selection for charging stations often employs static methods combining geographic information systems (GIS) with multi-criteria decision-making. This involves overlaying multi-source static data such as points of interest, road networks, population density, and grid constraints to identify candidate areas and select priority sites. While this approach effectively supports initial charging network coverage, its supply-side oriented nature fails to adequately characterize the dynamic and individual heterogeneous nature of user charging behavior, making it difficult to accurately predict actual operational performance after commissioning. In recent years, some studies have attempted to introduce dynamic big data such as traffic flow and vehicle trajectories to characterize the spatiotemporal distribution of charging demand and combine queuing theory models to optimize capacity allocation. However, these methods still focus on pre-operation prediction and planning, lacking a systematic assessment of the actual operational status of charging stations after commissioning, and failing to effectively integrate operational feedback into the site selection decision-making loop, resulting in a disconnect between optimization strategies and actual needs.

[0004] Therefore, it is necessary to provide a charging station deployment method that can integrate real operational data, quantify site pressure, identify spatial competition relationships, and make targeted optimization decisions based on the specific conditions of each site. Summary of the Invention

[0005] The purpose of this invention is to provide a charging station optimization deployment method based on operational status, so as to optimize deployment decisions in a targeted manner according to the operational status of the charging station.

[0006] In a first aspect, the charging station optimization deployment method based on operational status provided by the present invention includes: acquiring operational data of existing charging stations and constructing a saturation index based on the operational data; setting a neighborhood radius, determining a set of neighboring stations within the neighborhood radius for each charging station, calculating a siphon intensity index based on the saturation index of each station in the set of neighboring stations, identifying competitive advantage stations based on the saturation index, siphon intensity index, and competition situation of each charging station; extracting operational characteristics of each charging station and constructing an operational feature vector, performing cluster analysis based on the operational feature vector to classify the operational modes of charging stations; performing a multi-dimensional evaluation by comprehensively considering the saturation index, the results of identifying competitive advantage stations, and the clustering results of operational modes, and generating differentiated optimization deployment strategies based on the multi-dimensional evaluation results.

[0007] The beneficial effects of the charging station optimization deployment method based on operational status provided by this invention are: it can extract the value and bottlenecks of stations from real operational feedback, and promote the transformation of charging network planning from static coverage to a refined model of dynamic feedback and efficiency priority. By quantifying the operational pressure, competitive relationships and pattern characteristics of stations, it provides data-driven decision support for the optimization of existing stations and the layout of new stations.

[0008] In one possible embodiment, constructing a saturation index based on operational data includes: calculating the daily utilization rate of the charging station based on its charging service duration, number of charging sessions, and available parking spaces; calculating the charging station's capacity pressure, peak pressure, and flow pressure based on the daily utilization rate and operational data; and weighting and fusing the capacity pressure, peak pressure, and flow pressure according to preset weighting coefficients to obtain the saturation index, wherein the preset weighting coefficients for capacity pressure, peak pressure, and flow pressure are respectively... , and , ,and , and All are greater than 0.

[0009] In another possible embodiment, a charging station is determined to be a competitive advantage site when it simultaneously meets three criteria. The criteria include: the saturation index is in the top m% of all charging stations (10% ≤ m ≤ 30%); the number of neighboring stations within the neighborhood radius R is not less than a preset number threshold N; and the siphon intensity index is greater than or equal to a preset intensity threshold S. Wherein, m is determined based on the distribution characteristics of regional charging station operation data, R is determined based on the average block size of the urban built-up area and the acceptable travel distance for users, N is determined based on the regional competition density, and S is determined based on the market competition environment.

[0010] In other possible embodiments, extracting the operational characteristics of each charging station and constructing an operational feature vector includes: extracting the operational characteristics of each charging station including: average daily charging frequency, peak daily utilization rate, average daily utilization rate, average charging duration per charge, and average charging amount per charge; and constructing a five-dimensional feature vector from the extracted operational characteristics as the operational feature vector.

[0011] In one possible embodiment, based on the cluster analysis results, charging stations can be divided into multiple operating modes. The operating characteristics used for the division include the average daily number of charging sessions, daily utilization rate, and single charging duration of the charging station. The operating modes include: high turnover mode, low efficiency saturation mode, and stable operation mode.

[0012] In one possible embodiment, the differentiated optimization deployment strategy includes: a capacity expansion strategy: for charging stations in high-turnover mode, when the peak daily utilization rate exceeds a preset target threshold, the number of new service units is calculated and capacity is expanded; an efficiency improvement strategy: for charging stations in low-efficiency saturation mode, efficiency improvement measures are taken, including: upgrading a preset proportion of AC slow charging piles in the charging station to DC fast charging piles, and / or introducing an overtime billing mechanism, wherein the preset proportion is not less than 50%.

[0013] Secondly, the present invention also provides a charging station optimization deployment device based on operational status, comprising: a saturation index construction unit, used to acquire operational data of existing charging stations and construct a saturation index based on the operational data; a competitive advantage site identification unit, used to set a neighborhood radius, determine the set of neighboring sites within the neighborhood radius for each charging station, calculate a siphon intensity index based on the saturation index of each site in the set of neighboring sites, and identify competitive advantage sites based on the saturation index, siphon intensity index, and competition situation of each charging station; an operation mode clustering unit, used to extract the operational characteristics of each charging station and construct an operational feature vector, and perform cluster analysis based on the operational feature vector to classify the operation modes of charging stations; and an optimization strategy generation unit, used to perform multi-dimensional evaluation by comprehensively considering the saturation index, the competitive advantage site identification result, and the operation mode clustering result, and generate differentiated optimization deployment strategies based on the multi-dimensional evaluation result.

[0014] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for optimizing the deployment of charging stations based on operational status.

[0015] Fourthly, the present invention also provides an electronic device, comprising: a processor and a memory; the memory being used to store a computer program; the processor being used to execute the computer program stored in the memory, so that the electronic device performs the above-described charging station optimization deployment method based on operational status.

[0016] For the beneficial effects of the second to fourth aspects mentioned above, please refer to the description of the first aspect mentioned above. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a method for optimizing the deployment of charging stations based on operational status, provided in an embodiment of the present invention; Figure 2 A spatial distribution heatmap of CSSI values ​​for each charging station is provided as an embodiment of the present invention. Figure 3 An elbow-method curve diagram of the K-Means clustering algorithm provided in this embodiment of the invention; Figure 4 A radar map of various cluster features provided in an embodiment of the present invention; Figure 5 A multidimensional feature evaluation view provided in an embodiment of the present invention; Figure 6 A schematic diagram of a charging station optimization deployment device based on operational status provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of an electronic device structure provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions in the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art. The terms "comprising" and similar expressions used herein mean that the element or object preceding the word covers the element or object listed following the word and its equivalents, but do not exclude other elements or objects.

[0019] This embodiment provides a method for optimizing the deployment of charging stations based on operational status. See the appendix to the specification. Figure 1 The method includes: S101: Obtain operational data of existing charging stations and construct a saturation index based on the operational data.

[0020] In one possible embodiment, after obtaining the operational data of existing charging stations, the raw data needs to be preprocessed, and a saturation index is constructed based on the processed operational data. Preprocessing the raw data includes: deleting invalid records from the raw data; and correcting and supplementing ambiguous or missing classification labels.

[0021] In one possible embodiment, constructing a saturation index based on operational data includes: calculating the daily utilization rate of the charging station based on its charging service duration, number of charging sessions, and available parking spaces; calculating the charging station's capacity pressure, peak pressure, and flow pressure based on the daily utilization rate and operational data; and weighting and fusing the capacity pressure, peak pressure, and flow pressure according to preset weighting coefficients to obtain the saturation index, wherein the preset weighting coefficients for capacity pressure, peak pressure, and flow pressure are respectively... , and , ,and , and All are greater than 0.

[0022] For example, to obtain real daily operational data of charging stations in Nanchang City, the process of constructing a saturation index based on this operational data specifically includes: obtaining a dataset spanning from July 1, 2025 to July 31, 2025, covering 128 stations and a total of 3574 daily records. Preprocessing the original dataset: addressing the issue of a large-scale missing number of parking spaces (2508 invalid records) in the key variable "available parking spaces," all invalid records were removed; simultaneously, using the map POI interface, ambiguous or missing classification labels such as "region" and "electricity type" were corrected and supplemented, ultimately forming a dataset containing 36 stations and 1066 valid daily operational records. The daily utilization rate of each valid station in the preprocessed valid daily operational records was calculated. The daily utilization rate is calculated according to the following formula: ,in, Indicates the number of days The duration of the charging service (in hours). This indicates the total number of charging times for the day. This indicates the number of available parking spaces at the station. Daily utilization rate is a comprehensive measure of the station's resource availability, including charging, waiting, and temporary parking after charging is complete.

[0023] Based on daily utilization rate and operational data, the capacity pressure, peak pressure, and flow pressure of charging stations are calculated. Capacity pressure is defined as the monthly average daily utilization rate, peak pressure as the 90th percentile of the monthly daily utilization rate, and flow pressure as the monthly average number of charging sessions per day. Minimum-maximum normalization is applied to capacity pressure, peak pressure, and flow pressure, mapping them to... Interval: ,in, For the original indicators, and These are the minimum and maximum values ​​of this indicator across all 36 sites. The saturation index is obtained by weighted fusion of capacity pressure, peak pressure, and flow pressure, and the specific calculation follows the formula: Where CSSI represents saturation index, CS represents capacity pressure, PP represents peak pressure, and TP represents flow pressure. , , These are the capacity pressure weighting coefficient, peak pressure weighting coefficient, and flow pressure weighting coefficient, respectively, satisfying... ,and , , All values ​​are greater than 0. The weighting coefficients should be determined based on the regional operational characteristics and business priorities. The construction of the saturation index can overcome the limitations of a single utilization rate indicator and achieve accurate quantification of the operational pressure of each charging station.

[0024] In one possible embodiment, , and The values ​​range from 0.3 to 0.5.

[0025] S102: Set the neighborhood radius, determine the set of neighboring stations within the neighborhood radius for each charging station, calculate the siphon intensity index based on the saturation index of each station in the set of neighboring stations, and identify competitive advantage stations based on the saturation index, siphon intensity index and competition situation of each charging station.

[0026] In one possible embodiment, the neighborhood radius of the station is set to determine the charging station. The set of neighboring sites within the neighborhood radius The siphon intensity index of each station is calculated based on the saturation index of each station in the neighboring station set. The calculation of the siphon intensity index satisfies the following formula: ,in, Indicates charging station The siphon intensity index, Indicates charging station saturation index, Indicates nearby stations saturation index, This represents the number of stations in the set of neighboring stations. The siphon intensity index quantifies the strength of a charging station's market dominance by calculating the average ratio of the saturation of its surrounding competitive environment to that of the charging station itself. When the value is >, it indicates that the saturation of the target site is higher than the surrounding average, suggesting a siphon effect. The larger the value, the more significant the siphon effect.

[0027] The neighborhood radius R needs to be set by comprehensively considering the average block size of the urban built-up area and the acceptable travel distance for users. Generally speaking, R can be selected within the range of 1-3 kilometers. In the city center, where blocks are dense and users are sensitive to distance, a smaller R value (such as 1-1.5 kilometers) can be selected; in the suburbs or development areas, where users have a larger travel radius, a larger R value (such as 2.5-3 kilometers) can be selected.

[0028] In one specific embodiment, taking the setting of the neighborhood radius based on valid data from the obtained charging station operation data in Nanchang City as an example, considering that the average street size in the built-up area of ​​Nanchang City is about 1.5-2.5 kilometers, and electric vehicle users generally accept a short driving distance of 2-3 kilometers, the neighborhood radius R is set to 2 kilometers.

[0029] In one possible embodiment, based on the calculated siphon intensity index of the charging station, a discrimination criterion is established according to the saturation index, siphon intensity index and competition situation of each charging station to identify competitive advantage sites.

[0030] Specifically, the criteria for identifying a site with a competitive advantage include three core conditions: (1) The charging station itself is a high saturation site, that is, the saturation index of the charging station is in the top m% of all charging stations. m is usually selected in the range of 10%-30%, and is determined according to the distribution characteristics of regional charging station operation data. (2) There is effective competition in the surrounding area, that is, the number of neighboring stations within the neighborhood radius R is not less than the preset number threshold N. N is usually selected in the range of 1-5, and is determined according to the regional competition density. (3) Significant siphon intensity, that is, the siphon intensity index of the charging station is not less than the preset intensity threshold S. S is usually selected in the range of 1.5-3.0, and is determined according to the market competition environment.

[0031] Charging stations that meet all three of the above conditions are considered to have a competitive advantage.

[0032] For example, in the analysis of charging station operation data in Nanchang City, considering that: the overall saturation of charging stations in the city shows a significant head concentration effect, m=25% is set to screen out highly saturated stations; based on the aforementioned analysis, the neighborhood radius R=2 kilometers is set; the distribution density of charging stations in the region is moderate, and the threshold for the number of neighboring stations N=2 is set to ensure that there is a real competitive environment in the surrounding area; considering the intensity of market competition, the siphon intensity threshold S=2.0 is set, that is, the saturation of the target station is required to be at least twice the average of the surrounding area.

[0033] Therefore, the specific criteria are set as follows: when the saturation index of a charging station is in the top 25% of all charging stations, the number of neighboring stations within a 2-kilometer radius of the charging station is no less than 2, and the siphon intensity index is no less than 2, the charging station is judged to be a competitive advantage station.

[0034] Based on the above criteria, 36 effective charging stations in Nanchang City were identified, and 6 stations with competitive advantages were identified. Further analysis of the operational attributes of each station (such as charging rates, service rates, parking fees, and operating hours) revealed that the siphon effect of these competitive advantage stations is mainly driven by two types of differentiated competitive advantages: The first is cost-effectiveness advantage. These stations attract price-sensitive users by offering significantly lower overall charging costs (charging rate + service rate + parking fee) than surrounding stations. For example, a competitive advantage station may have an overall charging cost 15%-20% lower than surrounding stations, becoming a price haven in the area. The second is convenience advantage. These stations effectively reduce users' time costs and decision-making barriers by offering longer operating hours (such as 24-hour operation) and simpler parking rules (such as free parking or flexible parking duration). For example, a station may offer 24-hour service with no parking time restrictions, while surrounding stations only operate from 8:00 to 22:00 with a 2-hour parking limit, creating a significant convenience advantage.

[0035] The spatial distribution of the competitive advantage sites identified in this embodiment is shown in the appendix of the specification. Figure 2 As shown in the figure, spatially, five of the six competitive charging stations are concentrated in the southern part of Qingyunpu District and the Xiaolan Economic Development Zone of Nanchang County, a hotspot for operations. This area has high charging demand and fierce competition, allowing these stations to establish local market dominance by building differentiated advantages. In contrast, the Tianxiang charging station exists independently as a scattered point in the northeastern High-tech Zone, indicating that even in relatively dispersed areas, as long as there is high-density demand potential, it is possible to establish local market dominance by building differentiated advantages (such as leveraging the stable charging needs of employees in the High-tech Zone to provide cost-effectiveness).

[0036] S103: Extract the operational characteristics of each charging station and construct an operational characteristic vector. Perform cluster analysis based on the operational characteristic vector to classify the operational modes of the charging stations.

[0037] In one possible embodiment, extracting the operational characteristics of each charging station and constructing an operational feature vector includes: extracting the operational characteristics of each charging station including: average daily charging frequency, peak daily utilization rate, average daily utilization rate, average charging duration per charge, and average charging amount per charge; and constructing a five-dimensional feature vector from the extracted operational characteristics as the operational feature vector.

[0038] In one specific embodiment, the average daily number of charging times was extracted. Specifically defined as the average number of charging services per day during the research period, its calculation satisfies the following formula. Peak daily utilization rate The 90th percentile of daily utilization rates over the study period was used as a metric to reflect the operational pressure on the site under extreme loads; average daily utilization rate The arithmetic mean of daily utilization rate within the research period is used to measure the daily load level of the site; average charging time per charge. Defined as the ratio of total charging time to total charging times within the research period, it is a key indicator reflecting the service efficiency of the site and the turnover capacity of parking spaces; average charging amount per charge. To study the ratio of total charging amount to total number of charging times within a research cycle, and to characterize users' charging behavior habits; among which, Indicates the total number of days in the research period. Indicates the first The number of charging times per day. The five-dimensional feature vector extracted above is subjected to min-max normalization and mapped to... The interval is used to eliminate differences in dimensions, and after normalization, the final operational feature vector is obtained.

[0039] In one possible implementation, the K-Means clustering algorithm is used to classify charging stations into patterns based on operational feature vectors. The K-Means algorithm optimizes the clusters by iteratively minimizing the sum of squared distances from data points within a cluster to the cluster center, effectively identifying groups of charging stations with similar operational characteristics. To determine the optimal number of clusters k, the elbow method can be used for evaluation. This involves calculating the within-cluster sum of squares (WCSS) for different k values ​​and plotting the WCSS as a function of k. The value of k is determined at the point where the curve shows a clear inflection point (elbow shape), which balances intra-cluster compactness with model complexity.

[0040] In addition to the K-Means algorithm, other clustering algorithms can be used depending on the data characteristics and application requirements, such as Hierarchical Clustering, DBSCAN (Density-Based Spatial Clustering of Applications with Noise), and Gaussian Mixture Model (GMM).

[0041] In one possible implementation, based on cluster analysis results, charging stations can be classified into multiple operating modes. These different operating modes reflect differences in operational efficiency, service characteristics, and demand matching. The type and number of operating modes depend on the operational data characteristics of the charging stations in the region and the clustering parameter settings.

[0042] For example, in a certain application scenario, charging stations can be divided into the following three typical operating modes: (1) High Turnover Mode: The core characteristics of this type of charging station are extremely high daily charging frequency and extremely short single service duration, indicating that it provides efficient fast charging services and has a very high parking space turnover rate. It is usually located in high-traffic areas such as transportation hubs or commercial centers. This type of station has high service efficiency and can serve more users with limited parking space resources.

[0043] (2) Inefficient saturation mode: This type of charging station is characterized by an extremely long average charging time per session and a low average number of charging sessions per day, revealing that its saturation state is due to congestion caused by low service efficiency. The peak daily utilization rate is high, but the average daily utilization rate is relatively low, indicating that parking spaces are occupied for a long time, which may be located in areas with lax parking management or a lack of overtime billing mechanisms.

[0044] (3) Stable operation mode: All indicators of this type of charging station are at a medium or low level, and the operation is relatively stable. The daily utilization rate and number of charging times are at a medium level, and the amount of charging per charge is relatively high. It usually serves a stable user group in a specific destination (such as residential community or office park).

[0045] In other application scenarios, based on regional characteristics and data distribution, other operating models may also be identified. For example: Seasonal fluctuation pattern: The operating status of this type of charging station varies significantly with the season or holidays. The utilization rate increases significantly during specific periods (such as peak tourist seasons and holidays), while it remains at a low level at other times.

[0046] New growth model: These charging stations have a shorter operating time but a clear growth trend. The average number of daily charging sessions and utilization rate are showing a continuous upward trend, indicating that the charging demand in the area is growing rapidly.

[0047] Idle and inefficient mode: These charging stations are in a state of low utilization for a long time. The average number of daily charging times and utilization rate are significantly lower than the regional average, which may be due to improper site selection, insufficient surrounding demand, or intense competition.

[0048] In this embodiment, the K-Means clustering algorithm is used to classify the operation modes based on the operational data characteristics of 36 charging stations in Nanchang City.

[0049] For example, taking the classification of effective data from the operation data of charging stations in Nanchang City into operational modes, the five-dimensional operational feature vector is first standardized to eliminate the influence of different feature dimensions. Then, the elbow method is used to determine the optimal number of clusters, k. See the appendix of the instruction manual. Figure 3The figure shows the WCSS curve as a function of the k value. When k=3, the downward slope of the curve slows down significantly, forming a distinct elbow shape, indicating that k=3 is the optimal solution balancing intra-cluster compactness and model complexity. While further increasing the k value can further reduce WCSS, the improvement is limited and it increases model complexity and the risk of overfitting.

[0050] Based on the clustering results with k=3, the 36 stations were divided into three operating modes with significantly different characteristics. For ease of description and management, the stations in these three modes were named: high-turnover core hub, low-efficiency saturated long-duration station, and destination station, respectively.

[0051] See the instruction manual appendix Figure 4 The diagram uses different line types and marker styles to distinguish three operating modes, showcasing a radar chart comparison of the three modes across five operational characteristic dimensions. The core characteristic of high-turnover core hubs is their extremely high daily average charging frequency and extremely short single service duration, indicating that they provide efficient fast charging services and have extremely high parking space turnover. Inefficient, saturated, long-duration stations are characterized by extremely long average single service duration and low daily average charging frequency, revealing that their saturation state stems from congestion caused by low service efficiency. Destination stations have all indicators at moderate or low levels, indicating a relatively stable operating status.

[0052] It should be noted that the above three operating models are based on the characteristics of charging station operation data in Nanchang City and the clustering results of k=3. In other application scenarios, different numbers and types of operating models may be identified based on factors such as the number and distribution density of charging stations in the area and the characteristics of operation data. For example, in large cities with a greater number and wider distribution of charging stations (such as Beijing and Shanghai), it may be necessary to classify them into 4-5 operating modes to more finely characterize the operating characteristics of different stations. For example, it may be possible to further distinguish between "highway service stations" (serving long-distance transit vehicles) and "nighttime slow charging stations" (mainly providing slow charging services at night). In areas that include multiple scenarios such as urban centers, suburbs, and highway service areas, operating modes with obvious scenario characteristics may be identified, such as "highway service mode" (large single charge volume, short charging time, and short user dwell time) and "suburban slow charging mode" (low utilization rate, long single charge time, mainly slow charging). In data sets with a long operating time span, operating modes that reflect life cycle characteristics may be identified, such as "new growth mode" (short operating time but obvious growth trend) and "decline mode" (continuously declining utilization rate).

[0053] The technical solution of the present invention does not limit the specific type and number of operating modes, and the clustering parameters and mode division methods can be flexibly adjusted according to the actual application scenario and business needs.

[0054] S104: A multi-dimensional evaluation is conducted based on the comprehensive saturation index, competitive advantage site identification results, and operation mode clustering results. Based on the multi-dimensional evaluation results and the operation mode characteristics of the charging stations, a differentiated optimization deployment strategy is generated.

[0055] In one possible embodiment, after completing the construction of the saturation index of charging stations, the identification of competitive advantage sites, and the clustering of operation modes, a multi-dimensional evaluation view is constructed by integrating the saturation index, the identification results of competitive advantage sites, and the clustering results of operation modes. This view provides an integrated and visual presentation of the overall operation status of each site, offering an intuitive basis for generating differentiated optimization strategies.

[0056] Multidimensional evaluation views can be constructed using various visualization methods, such as scatter plots, heatmaps, radar charts, or combinations of methods. A typical implementation is the use of an enhanced bubble chart, which simultaneously displays information from multiple operational dimensions through multiple visual encodings such as location, size, and color.

[0057] For example, the multi-dimensional evaluation view constructed using the information obtained from S101-S103 can be spatially mapped using a two-dimensional coordinate system: the average number of daily charging sessions is used as the horizontal axis to reflect the station's traffic volume and user attractiveness; the average charging time per session is used as the vertical axis to characterize the station's service efficiency and parking space turnover capacity. In this coordinate system, each charging station is represented as a bubble, and its position is uniquely determined by the two core indicators mentioned above.

[0058] In one possible implementation, differentiated optimization deployment strategies are generated based on multi-dimensional evaluation results and the operational characteristics of the charging stations. The formulation of these optimization strategies follows the principle of "tailored measures for each station and precise intervention," designing targeted optimization measures based on the characteristics and nature of the problems in different operational models. (1) Expansion Strategy: This strategy is suitable for charging stations with high daily charging frequency, short charging duration, and high parking space turnover rate. The high saturation of these stations stems from the huge traffic attracted by efficient services, making them high-value nodes with the best operational efficiency. When their peak daily utilization rate continuously exceeds the preset target threshold, an expansion procedure should be initiated to add service units. The number of new service units can be dynamically determined through a preset calculation formula, taking into account factors such as current utilization rate, target threshold, and existing scale.

[0059] (2) Efficiency Improvement Strategy: This strategy is applicable to charging stations operating in an inefficient, saturated mode characterized by high peak day utilization, long single-charge duration, and congestion. The high saturation of these stations stems from low parking space turnover efficiency due to extremely long average single-charge durations, rather than insufficient capacity. The optimization strategy should focus on improving service efficiency. Specific measures include: at the hardware level, upgrading a predetermined proportion (e.g., 50% or higher) of AC slow-charging piles to DC fast-charging piles to shorten single-charge durations; at the management level, introducing an overtime billing mechanism, setting standard service durations, and implementing tiered billing or double charges for exceeding the time limit to economically suppress ineffective parking space occupation; and at the technical level, introducing an intelligent scheduling system to optimize charging resource allocation and reduce waiting time.

[0060] (3) Maintenance Strategy: Applicable to charging stations with moderate daily utilization and charging frequency, and stable operation. These stations typically serve a stable user base at specific destinations, with all operational indicators at low to medium levels and stable. Currently, it is recommended to maintain the status quo and continuously monitor operational data trends to avoid unnecessary investment. If subsequent data shows increased demand or decreased efficiency, the strategy can be adjusted accordingly.

[0061] (4) Transformation or exit strategy: For charging stations that have been in a state of low utilization for a long time, with the average number of daily charging and utilization rate significantly lower than the regional average, it is advisable to adjust the operation mode (such as converting to an emergency backup site), relocate to an area with higher demand, or exit operation after evaluation.

[0062] Furthermore, for incremental deployments, operational hotspots and potential scenarios should be identified based on multi-dimensional evaluation results, and precise site selection should be carried out for scenarios with stable demand. Priority should be given to deploying new sites that can generate high turnover characteristics, such as setting up fast charging stations in high-traffic areas like transportation hubs, commercial centers, and logistics parks; or setting up slow charging stations for specific destinations such as residential communities and office parks to serve a stable user base.

[0063] In one specific embodiment, a multi-dimensional evaluation view is constructed based on the operational data of 36 charging stations in Nanchang City, and differentiated optimization deployment strategies are generated.

[0064] An enhanced bubble chart is used to construct a multi-dimensional evaluation view, forming the result shown in the appendix to the instruction manual. Figure 5 The multidimensional evaluation view is shown. In this view, the horizontal axis represents the average number of charges per day, and the vertical axis represents the average number of charges per charge. The bubble size reflects the CSSI value. Figure 5 The multidimensional evaluation view shown clearly reveals two highly saturated modes with very different properties: Stations located in the upper left corner (such as the Jiangling Jingtai Garden charging station) exhibit significantly higher average charging times per session and lower average daily charging frequency, showing large bubbles but indicating an inefficient saturation mode. This suggests that their high saturation is due to congestion caused by inefficient service, rather than strong market demand. Further analysis reveals that the charging stations at this site lack overtime billing mechanisms, resulting in some vehicles occupying parking spaces for extended periods even after being fully charged.

[0065] Stations located in the lower right corner (such as the Changnan charging station) exhibit extremely high daily charging frequency and extremely short single service duration. Their bubbles are also relatively large, but they represent a high-turnover model. This reveals that their high saturation is a positive result of efficient service attracting massive traffic, making them high-value nodes with the best operational efficiency within the region.

[0066] Most sites operating smoothly are concentrated in the lower left corner of the regular development zone, where traffic, efficiency, and saturation are all at low levels, indicating stable operation. These sites are mainly located in residential areas and office parks, serving a fixed user base.

[0067] Based on the analysis results of the multi-dimensional evaluation view, differentiated optimization deployment strategies are generated for charging stations with different operating models: Optimization and deployment analysis for high-turnover core hub sites: These sites are characterized by high daily charging frequency and short single service duration. Their high saturation stems from the massive traffic attracted by efficient service, making them high-value nodes with the best operational efficiency. For high-turnover core hub sites, when their peak daily utilization rate... Continuously exceeding the preset target threshold When the expansion process is initiated, new service units are added. The number of new service units is specified. Calculated dynamically using the following formula: ,in, This indicates the number of existing service units (i.e., parking spaces) at the site.

[0068] An analysis of the optimized deployment of inefficient, saturated charging stations reveals that their high saturation stems from extremely long average charging times per session, leading to low parking space turnover efficiency, rather than insufficient capacity. Therefore, the optimization strategy should focus on improving efficiency. Specific optimization measures include: 1) At the hardware level, upgrading at least 50% of the AC slow charging piles in the stations to DC fast charging piles; 2) At the management level, introducing an overtime billing mechanism, setting a standard service time, and doubling the charge for exceeding the time limit to economically curb ineffective parking space occupation.

[0069] For destination stations that account for a large proportion, their various operational indicators are at a low to medium level and are stable. It is recommended to maintain the status quo and continue to observe the trend of changes in their operational data.

[0070] In addition, for incremental deployments, precise site selection should be carried out in the identified operational hotspot areas, targeting stable demand scenarios, and new sites that can form high-turnover core hubs should be prioritized.

[0071] The generation of differentiated optimization deployment strategies based on multidimensional evaluation results realizes a closed loop from "data evaluation" to "strategy generation," providing actionable decision support for the refined operation and scientific planning of charging networks.

[0072] This invention provides a charging station optimization deployment method based on operational status. By constructing a charging station saturation index that integrates capacity, peak traffic, and flow pressure, it achieves precise quantification of the comprehensive operational pressure of charging stations, overcoming the limitation of a single utilization rate indicator that cannot distinguish between "high efficiency and high load" and "low efficiency and congestion." For the first time, it achieves operational identification of the "siphon effect" in the micro-market through the criteria for identifying competitive advantage sites, revealing the formation mechanism of competitive advantage driven by cost-effectiveness or convenience. By extracting the operational characteristics of charging stations and systematically classifying them into different operational modes based on these characteristics, it provides a pattern recognition foundation for refined management. Cross-analysis of the saturation index, the results of identifying competitive advantage sites, and the clustering results of operational modes generates differentiated optimization suggestions for "expansion" or "efficiency improvement" for different modes of sites, effectively avoiding "one-size-fits-all" modifications and significantly improving the overall efficiency and supply-demand matching of the charging network.

[0073] By applying the charging station operation status-based optimization deployment method of this invention to process charging station operation data, it is possible to uncover the value and bottlenecks of stations from real operational feedback, and promote the transformation of charging network planning from static coverage to a refined model of dynamic feedback and efficiency priority. By quantifying the operational pressure, competitive relationships, and pattern characteristics of stations, it provides data-driven decision support for the optimization of existing stations and the layout of new stations.

[0074] See the instruction manual appendix Figure 6 This embodiment also provides a charging station optimization deployment device based on operational status, which is used to implement the above method embodiment. The device includes: The saturation index construction unit 201 is used to obtain the operation data of existing charging stations and construct a saturation index based on the operation data.

[0075] The competitive advantage site identification unit 202 is used to calculate the siphon intensity index based on the saturation index and identify competitive advantage sites based on the saturation index, siphon intensity index and competition situation of each charging station.

[0076] The operation mode clustering unit 203 is used to extract the operation characteristics of each charging station and construct the operation feature vector. Cluster analysis is performed based on the operation feature vector to classify the operation modes of the charging stations.

[0077] The optimization strategy generation unit 204 is used to perform multi-dimensional evaluation by comprehensively considering the saturation index, competitive advantage site identification results, and operation mode clustering results, and generate differentiated optimization deployment strategies based on the multi-dimensional evaluation results.

[0078] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0079] In other embodiments of this application, an electronic device is disclosed, such as... Figure 7 As shown, the electronic device 300 may include: one or more processors 301; a memory 302; a display 303; one or more application programs (not shown); and one or more computer programs 304. These devices can be connected via one or more communication buses 305. The one or more computer programs 304 are stored in the memory and configured to be executed by the one or more processors 301. The one or more computer programs 304 include instructions that can be used to perform actions such as... Figure 1 And the various steps in the corresponding embodiments.

[0080] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0081] In the embodiments of this application, the functional units can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0082] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as flash memory, portable hard disk, read-only memory, random access memory, magnetic disk, or optical disk.

[0083] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the claims.

Claims

1. A method for optimizing deployment of charging stations based on operating status, characterized in that, The method comprises the following steps: acquiring operation data of existing charging stations, and constructing a saturation index based on the operation data; setting a neighborhood radius, determining a set of neighboring stations within the neighborhood radius for each charging station, calculating a siphon strength index based on the saturation index of each station in the set of neighboring stations, and identifying a competitive advantage station according to the saturation index, the siphon strength index and the competition situation of each charging station; extracting operation characteristics of each charging station and constructing an operation characteristic vector, and performing cluster analysis according to the operation characteristic vector to divide the operation mode of the charging station; performing multi-dimensional evaluation by comprehensively considering the saturation index, the identification result of the competitive advantage station and the cluster result of the operation mode, and generating a differentiated optimization deployment strategy according to the multi-dimensional evaluation result; wherein the saturation index is constructed based on the operation data, which comprises the following steps: calculating the daily utilization rate of the charging station based on the charging service time, the number of charging times and the number of available parking spaces of the charging station; calculating the capacity pressure, peak pressure and flow pressure of the charging station based on the daily utilization rate and the operation data; The saturation index is obtained by weighting and fusing the capacity pressure, the peak pressure and the flow pressure according to preset weight coefficients, wherein the preset weight coefficients of the capacity pressure, the peak pressure and the flow pressure are respectively , and , , and , and are greater than 0.

2. The method of claim 1, wherein, when the charging station meets three judgment conditions at the same time, it is determined that the charging station is a competitive advantage station, and the judgment conditions comprise: the saturation index is located in the front m% of all charging stations, and 10%≤m≤30%; the number of neighboring stations within the neighborhood radius R is not less than a preset number threshold N; the siphon strength index is greater than or equal to a preset strength threshold S; wherein m is determined according to the distribution characteristics of regional charging station operation data, R is determined according to the average block scale of the urban built-up area and the user acceptable travel distance, N is determined according to the regional competition density, and S is determined according to the market competition environment.

3. The method of claim 1, wherein, extracting operation characteristics of each charging station and constructing an operation characteristic vector, which comprises the following steps: extracting operation characteristics of each charging station, including daily average charging times, peak daily utilization rate, average daily utilization rate, single average charging time and single average charging capacity; the extracted operation characteristics are constructed into a five-dimensional feature vector as the operation characteristic vector.

4. The method of claim 1, wherein, The cluster analysis divides the charging stations into multiple operation modes according to the operation characteristics of the charging stations; the operation modes include high flow mode, low efficiency saturation mode, stable operation mode, seasonal fluctuation mode, new growth mode and idle low efficiency mode.

5. The method of claim 4, wherein The differentiated optimization deployment strategy comprises: expansion strategy: for the charging station in the high flow mode, when the peak daily utilization rate exceeds the preset target threshold, the number of new service units is calculated and expansion is carried out; efficiency improvement strategy: for the charging station in the low efficiency saturation mode, efficiency improvement measures are taken, which include upgrading a preset proportion of alternating current slow charging piles in the charging station to direct current fast charging piles, and / or introducing an overtime charging mechanism, wherein the preset proportion is not less than 50%.

6. An operating state-based charging station optimal deployment apparatus, characterized by, The device comprises: a saturation index construction unit for acquiring operation data of existing charging stations and constructing a saturation index based on the operation data; a competitive advantage station identification unit for setting a neighborhood radius, determining a set of neighboring stations within the neighborhood radius for each charging station, calculating a siphon strength index based on the saturation index of each station in the set of neighboring stations, and identifying a competitive advantage station according to the saturation index, the siphon strength index and the competition situation of each charging station; The operation mode clustering unit is configured to extract operation characteristics of each charging station and construct an operation characteristic vector, and perform clustering analysis based on the operation characteristic vector to divide operation modes of the charging stations; The optimization strategy generation unit is configured to perform multi-dimensional evaluation based on the saturation index, the competitive advantage site identification result, and the operation mode clustering result, and generate a differentiated optimization deployment strategy based on a multi-dimensional evaluation result; The saturation index is constructed based on the operation data, including: The daily utilization rate of the charging station is calculated based on the charging service duration, the charging frequency, and the number of available parking spaces of the charging station; The capacity pressure, the peak pressure, and the flow pressure of the charging station are calculated based on the daily utilization rate and the operation data; The saturation index is obtained by weighting and fusing the capacity pressure, the peak pressure and the flow pressure according to preset weight coefficients, wherein the preset weight coefficients of the capacity pressure, the peak pressure and the flow pressure are respectively , and , , and , and are greater than 0.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the operation state-based charging station optimization deployment method in any one of claims 1 to 5.

8. An electronic device, comprising: The computer program is executed by the processor to implement the operation state-based charging station optimization deployment method in any one of claims 1 to 5. The computer program is executed by the processor to implement the operation state-based charging station optimization deployment method in any one of claims 1 to 5. The computer program is executed by the processor to implement the operation state-based charging station optimization deployment method in any one of claims 1 to 5. ​

Images