An intelligent site selection and evaluation method and system for charging piles

Abstract

The present application provides a method and system for intelligent site selection and evaluation of charging piles. Among them, by obtaining the communication data of mobile terminals in the target area in real time, a demand time period division model is constructed to distinguish between daytime fast charging and nighttime regular charging demands; based on the demand distribution, the position of the edge computing device is dynamically adjusted to ensure that its service range matches the peak area of the pedestrian flow density in real time; according to the identified type of charging demand, the multi-port wireless charging system is controlled to switch to the adapted charging power mode; a set of candidate charging pile layout positions is generated by combining the device layout and power mode data, and the optimal deployment plan is selected through safety distance verification. The technical solution provided by the present application realizes the efficient matching of the charging pile layout and the dynamic pedestrian flow demand, and improves the daytime charging efficiency and nighttime device utilization rate.

Description

Technical Field

[0001] This application relates to the technical field of intelligent site selection and evaluation, and particularly to a method and system for intelligent site selection and evaluation of charging piles. Background Art

[0002] There are significant differences in charging demands between daytime office use and nighttime residential use in urban mixed-use areas (such as commercial-residential complexes and properties above subway stations). During the day, it is necessary to meet the rapid charging needs of business vehicles with short-term high power, while at night, it is necessary to adapt to the long-term regular charging needs of residential vehicles. Such scenarios require the charging pile layout plan to be able to respond to real-time changes in the flow of people, achieve efficient allocation of charging resources within a limited space, and at the same time avoid conflicts with underground pipe networks and balance fluctuations in grid load, which poses comprehensive technical challenges to dynamic demand perception, collaborative optimization of spatial resources, and energy efficiency adaptation.

[0003] Current mainstream solutions are based on static charging demand prediction models. By integrating historical charging order data and fixed time period division rules (such as weekdays / holidays), and combining with the grid capacity distribution data of the Geographic Information System (GIS), a multi-objective optimization algorithm is used to generate the location of charging piles. This solution sets a fixed power distribution ratio for daytime and nighttime, and uses genetic algorithms or particle swarm optimization algorithms to search for location selection plans that meet grid capacity constraints and maximize coverage within a preset geographical range.

[0004] The existing solutions have the following defects: the static model cannot capture real-time fluctuations in the density of the flow of people (such as a sudden surge in charging demand caused by a commercial event), resulting in coexistence of overloading of equipment during the day and idle resources at night; the fixed power distribution mode ignores the power characteristic differences in charging demands at different times, and it is difficult to achieve high energy efficiency operation (such as the conflict between fast charging demand during the day and peak load of the power grid); relying on offline optimization results, it is impossible to dynamically adjust the equipment location to avoid newly discovered underground pipe network conflicts during construction, and frequent manual intervention is required to modify the plan. Summary of the Invention

[0005] This application provides a method and system for intelligent site selection and evaluation of charging piles to solve the problem of low charging efficiency during the day and low utilization rate of equipment at night in the prior art.

[0006] In a first aspect, this application provides a method for intelligent site selection and evaluation of charging piles, including:

[0007] Obtain the communication data of mobile terminals in the target area, and generate a demand time period division model based on the spatio-temporal variation law of the density of the flow of people in the mobile terminal communication data. The demand time period division model is used to distinguish the fast charging demand corresponding to the daytime period from the regular charging demand corresponding to the nighttime period;

[0008] Adjust the positions of the edge computing devices deployed in the target area according to the demand distribution results output by the demand period division model, so that the service ranges of the edge computing devices move in unison with the peak areas of the pedestrian flow density;

[0009] Based on the charging demand types identified in the position adjustment results, control the multi-port wireless charging system to switch the charging power output mode, and the charging power output mode corresponds to the periods of the fast charging demand and the regular charging demand;

[0010] Combine the network layout data after the position adjustment of the edge computing devices with the information corresponding to the power output mode of the multi-port wireless charging system to generate a set of candidate charging pile layout positions;

[0011] Perform distance verification on each position in the set of candidate charging pile layout positions, and screen out the target charging pile layout plan that meets the preset safety standards and matches the demand distribution law of the demand period division model.

[0012] Optionally, the combining the network layout data after the position adjustment of the edge computing devices with the power output mode information of the multi-port wireless charging system to generate a set of candidate charging pile layout positions includes:

[0013] Extract the network layout data after the position adjustment of the edge computing devices, and identify the continuous spatial areas that meet the requirements of daytime charging service efficiency;

[0014] Synchronously obtain the power output mode information of the multi-port wireless charging system, and mark the output areas where the power utilization rate is continuously higher than the average level during the night period;

[0015] Perform geospatial overlay on the continuous spatial areas and the output areas, and screen out the candidate layout ranges that simultaneously include the boundaries of the daytime efficiency areas and the core areas of night utilization;

[0016] Based on the candidate layout ranges, perform spatial priority sorting on the deployable areas according to the preset charging pile spacing rules to generate a set of candidate charging pile layout positions.

[0017] Optionally, the performing distance verification on each position in the set of candidate charging pile layout positions, and screening out the target charging pile layout plan that meets the preset safety standards and matches the demand distribution law of the demand period division model includes:

[0018] Obtain the spatial distances between each position in the set of candidate charging pile layout positions and the three-dimensional coordinate data of the underground pipe network, and screen out the subset in which the straight-line distances from each position to the gas pipeline and the power pipe gallery are both greater than the preset safety distance;

[0019] Based on the spatial distribution of the fast charging demand hotspots and regular charging demand hotspots marked in the demand period division model, calculate the proportion of the area covered by the two types of demand hotspots in the subset, and retain the adaptation positions where the area proportion simultaneously meets the lower limits of daytime fast demand and nighttime regular demand coverage;

[0020] Verify the safety distance of the underground pipe network for the adaptation positions, eliminate abnormal positions where the distance from adjacent pipe network positions exceeds the preset distance range, and generate an intermediate layout plan set;

[0021] Conduct a safety assessment based on the historical period pedestrian flow density curve in the intermediate layout plan set, perform similarity matching between the inspection results and the demand distribution law of the demand period division model, and screen out the target charging pile layout plan that meets the preset safety standards and matches the demand distribution law.

[0022] Optionally, adjusting the position of the edge computing device deployed in the target area according to the demand distribution result output by the demand period division model includes:

[0023] Analyze the demand distribution result output by the demand period division model, extract the high-demand area coordinate set in the target area during the current period, and determine the movement trajectory of the peak area of the pedestrian flow density according to the spatio-temporal distribution characteristics of the high-demand area coordinate set;

[0024] Based on the center positions of the peak areas in each time segment of the movement trajectory, calculate the target deployment position set of the edge computing device, and the straight-line distance between each target position in the target deployment position set and the center of the peak area corresponding to the time segment does not exceed the preset coverage radius;

[0025] Generate a device migration instruction according to the target deployment position set, drive the edge computing device to migrate to the target position according to the device migration instruction, and establish a communication network with adjacent devices during the migration process, and control the end-to-end transmission delay between nodes in the communication network to be lower than the preset maximum value;

[0026] Obtain the updated coordinate set of the peak area through the communication network. When it is detected that the coverage overlap rate between the updated coordinate set and the target deployment position set is lower than the preset tolerance threshold, recalculate the target deployment position set based on the updated coordinate set and synchronously adjust the device migration instruction.

[0027] Optionally, controlling the multi-port wireless charging system to switch the charging power output mode based on the charging demand type identified in the position adjustment result includes:

[0028] Obtain the charging demand types marked in the position adjustment result, where the charging demand types include a first type of demand signal and a second type of demand signal corresponding to the fast charging demand and the regular charging demand respectively;

[0029] According to the spatial distribution density of the charging demand types, configure a priority matching rule for each charging port of the multi-port wireless charging system, where the charging ports in the area covered by the first type of demand signal have a higher priority than the second type of demand signal;

[0030] Based on the priority matching rule, adjust the electromagnetic coupling parameter combinations of each charging port in the multi-port wireless charging system so that the output power range of the high-priority charging ports adapts to the fast charging demand, and the output power range of the low-priority charging ports adapts to the regular charging demand. The electromagnetic coupling parameter combinations include the resonant frequency matching range and the power transfer coil spacing;

[0031] Through the electromagnetic coupling state feedback data of the multi-port wireless charging system, periodically detect the adaptation degree of the actual output power of each charging port to the priority matching rule. If it is detected that the adaptation degree is lower than the requirement of the matching rule, regenerate the electromagnetic coupling parameter combination and update the priority matching rule.

[0032] Optionally, the generating a demand period division model based on the spatio-temporal variation law of the population flow density in the mobile terminal communication data includes:

[0033] Extract the spatial coordinates and timestamps of the terminal devices in the mobile terminal communication data, and construct a spatio-temporal distribution sequence of the population flow density with geographical grids as units;

[0034] Perform pattern recognition on the population flow density fluctuation characteristics in each geographical grid in the spatio-temporal distribution sequence of the population flow density, and extract the grid set with short-term high-density aggregation characteristics during the daytime period as the fast charging demand candidate area, and the grid set with continuous medium and low density distribution during the nighttime period as the regular charging demand candidate area;

[0035] Based on the spatio-temporal overlap degree analysis of the fast charging demand candidate area and the regular charging demand candidate area, merge the candidate areas with spatial coverage areas exceeding the overlap degree upper limit in adjacent time segments into demand period division units, and label each division unit with the corresponding charging demand type label;

[0036] According to the label distribution law of the demand period division units in the historical period, correct the division granularity of the geographical grids and the determination threshold of the spatio-temporal overlap degree analysis, and generate a demand period division model that adapts to the population flow change characteristics in the target area.

[0037] Optionally, generating a device migration instruction according to the set of target deployment locations, driving the edge computing device to migrate to the target location according to the device migration instruction, and establishing a communication network with adjacent devices during the migration process, and controlling the end-to-end transmission delay between nodes in the communication network to be lower than a preset maximum value, including:

[0038] Generating a device migration instruction including a migration path and a migration speed according to the relative distance between each target location in the set of target deployment locations and the current location of the edge computing device;

[0039] Driving the edge computing device to migrate to the target location according to the device migration instruction, detecting the signal strength of adjacent edge computing devices during the migration process, and selecting adjacent devices with a signal strength higher than a preset threshold as candidate nodes for the communication network;

[0040] Based on the location distribution and signal strength data of the candidate nodes, constructing a star-shaped communication network topology centered on the edge computing device;

[0041] Monitoring the end-to-end transmission delay between each topology node in the star-shaped communication network topology, and if it is detected that the end-to-end transmission delay exceeds the preset maximum value, reselecting the candidate nodes and adjusting the hop count distribution of the star-shaped communication network topology.

[0042] Optionally, adjusting the electromagnetic coupling parameter combinations of each charging port in the multi-port wireless charging system so that the output power range of the high-priority charging port adapts to the fast charging requirement, and the output power range of the low-priority charging port adapts to the normal charging requirement, including:

[0043] According to the spatial distribution of different-priority charging ports marked in the priority matching rule, extracting the spatial density parameter of the fast charging requirement within the coverage area of the high-priority charging port;

[0044] Based on the spatial density parameter, configuring a narrowband resonance frequency range and a small-spacing power transmission coil parameter combination for each high-priority charging port, so that the output power range of the high-priority charging port covers the power interval corresponding to the fast charging requirement;

[0045] Synchronously configuring a broadband resonance frequency range and a large-spacing power transmission coil parameter combination for the low-priority charging port, so that the output power range of the low-priority charging port covers the power interval corresponding to the normal charging requirement;

[0046] Collecting the actual output power fluctuation data of different-priority charging ports, and if it is detected that the deviation from the corresponding power interval, recalculating the resonance frequency range and the power transmission coil spacing parameter combination based on the current fluctuation data.

[0047] In a second aspect, the present application provides a smart charging pile location evaluation system, including:

[0048] An acquisition module, configured to acquire mobile terminal communication data of a target area, generate a demand period division model based on the spatio-temporal variation law of the population flow density in the mobile terminal communication data, and the demand period division model is used to distinguish the fast charging demand corresponding to the daytime period from the regular charging demand corresponding to the nighttime period;

[0049] An adjustment module, configured to adjust the position of the edge computing device deployed in the target area according to the demand distribution result output by the demand period division model, so that the service range of the edge computing device moves in accordance with the peak area of the population flow density and meets the preset data transmission performance requirements;

[0050] A control module, configured to control the multi-port wireless charging system to switch the charging power output mode based on the charging demand type identified in the position adjustment result, and the charging power output mode corresponds to the periods of the fast charging demand and the regular charging demand;

[0051] A generation module, configured to combine the network layout data after the position adjustment of the edge computing device with the power output mode information of the multi-port wireless charging system to generate a set of candidate charging pile layout positions that simultaneously meet the daytime charging service efficiency and nighttime device utilization rate optimization indicators;

[0052] A screening module, configured to verify the safety distance of the underground pipe network for each position in the set of candidate charging pile layout positions, and screen out a target charging pile layout scheme that meets the preset construction safety standards and matches the demand distribution law of the demand period division model.

[0053] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a smart charging pile location evaluation method as described in the first aspect above.

[0054] In the embodiment of the present application, mobile terminal communication data of a target area is obtained, and a demand period division model is generated based on the spatio-temporal variation law of the population flow density in the mobile terminal communication data. The demand period division model is used to distinguish the fast charging demand corresponding to the daytime period from the regular charging demand corresponding to the nighttime period; according to the demand distribution result output by the demand period division model, the position of the edge computing device deployed in the target area is adjusted so that the service range of the edge computing device is kept consistent with the peak area of the population flow density; based on the charging demand type identified in the position adjustment result, the multi-port wireless charging system is controlled to switch the charging power output mode, and the charging power output mode corresponds to the periods of the fast charging demand and the regular charging demand; combining the network layout data after the position adjustment of the edge computing device with the information corresponding to the power output mode of the multi-port wireless charging system, a set of candidate charging pile layout positions is generated; distance verification is performed on each position in the set of candidate charging pile layout positions, and a target charging pile layout scheme that meets the preset safety standard and matches the demand distribution law of the demand period division model is selected.

[0055] The technical solution of the present application has the following beneficial effects:

[0056] Based on the spatio-temporal variation law of real-time population flow density, a dynamic demand model is constructed to accurately distinguish between daytime fast charging and nighttime regular charging demands, improving the accuracy of demand perception and period division; by migrating the position of the edge device in real time to match the peak area of the population flow, it is ensured that the computing resources are dynamically aligned with the high-demand area, reducing data transmission latency and improving service response efficiency; the charging power output is configured differently according to the demand type to achieve an adaptive switch between the fast charging and regular charging modes, solving the problems of device vacancy and grid load imbalance; combining the device layout and power mode data, a spatial candidate area that meets both daytime efficiency and nighttime utilization rate is selected, avoiding resource waste caused by a single index; through safety distance constraints and matching the demand distribution law, conflict areas of underground pipe networks are excluded and the device spacing is optimized, ensuring the safety and demand adaptability of the deployment scheme.

[0057] Furthermore, based on the adjusted network layout data of the edge computing device, identify the daytime efficient areas that contain the peak points of pedestrian flow density and the minimum service radius; simultaneously obtain the high-utilization output areas of the wireless charging system at night (the overlapping range of coil coverage and demand hotspots), and screen out the candidate layout ranges that cover both the daytime efficiency boundary and the night core area through geospatial overlay; combine the charging pile spacing rules to prioritize the candidate areas and generate a set of layout positions that take into account dynamic demand adaptation and engineering feasibility. Through spatial overlay and priority sorting, the collaborative optimization of daytime charging efficiency and night device utilization is achieved, while avoiding underground pipe network conflicts and over-dense equipment problems, and improving the dynamic adaptation ability and long-term operation and maintenance stability of the charging pile layout scheme in the mixed functional area.

[0058] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0060] Figure 1 Shows a flowchart of a method for intelligent site selection and evaluation of charging piles provided by the present application;

[0061] Figure 2 Shows a schematic structural diagram of a system for intelligent site selection and evaluation of charging piles provided by the present application;

[0062] Figure 3 Shows a schematic structural diagram of a computing device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] In order to enable those skilled in the art to better understand the solution of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application.

[0064] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0065] Researchers found that the current method for locating charging piles has significant shortcomings in terms of dynamic demand response and resource collaborative optimization. Especially for urban mixed-use areas with significant differences in daytime and nighttime charging demands, existing solutions are difficult to track the fluctuations in population flow density in real time, resulting in rigid charging pile layouts, unbalanced equipment utilization rates, and exacerbated peak-valley contradictions in the power grid load. Based on this, a method for intelligent location assessment of charging piles is provided. Specifically, a spatio-temporal demand division model is constructed through mobile terminal communication data, dynamically driving the migration of edge computing devices to match peak population flow areas, and regulating the power mode of the wireless charging system based on real-time demand types. Finally, a safe and adaptable layout plan is generated by combining equipment layout and power characteristics. This method can achieve high-precision matching of charging resources and dynamic demands, synchronously optimize daytime fast charging efficiency and nighttime equipment utilization rates, and effectively avoid construction safety hazards.

[0066] The technical solution of this application is applicable to scenarios where the charging demand differences between daytime office work and nighttime residence are balanced in urban mixed-use areas (such as commercial and residential complexes, properties above subway stations).

[0067] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of protection of this application.

[0068] Figure 1 The following is a flowchart of a method for intelligent location assessment of charging piles provided for the embodiments of this application, as Figure 1 shown, the method includes:

[0069] 101. Obtain the mobile terminal communication data of the target area, and generate a demand period division model based on the spatio-temporal change law of the population flow density in the mobile terminal communication data. The demand period division model is used to distinguish the fast charging demand corresponding to the daytime period from the regular charging demand corresponding to the nighttime period;

[0070] In this step, the demand period division model is a decision-making model constructed based on the spatio-temporal variation law of the pedestrian flow density in the mobile terminal communication data, and is used to divide the target area into a daytime fast charging demand dominant period and a nighttime regular charging demand dominant period.

[0071] In the embodiment of the present application, the anonymous signaling data (including the terminal device location, stay duration, and movement trajectory) collected by the communication base station is used to statistically calculate the pedestrian flow density of each grid cell in units of time windows. The hierarchical clustering algorithm is used to perform spatial aggregation on the high-density areas, and the adjacent periods with the same fluctuation pattern are identified by combining time series similarity analysis. The state transition probability algorithm is used to model the demand switching nodes between daytime and nighttime, and finally a demand period division model including period boundaries and demand intensity labels is generated.

[0072] Suppose the mobile terminal signaling data of the garage on the B1 floor of a commercial and residential complex shows that during the period from 8:00 to 10:00 on weekdays, the number of active terminals increases from 500 to 1800 every 15 minutes, and the median stay duration increases from 3 minutes to 25 minutes; while during the period from 20:00 to 22:00, the number of active terminals stabilizes at about 300, and the median stay duration reaches 120 minutes. The demand period division model marks 8:00 - 20:00 as the "daytime fast charging demand period" (pedestrian flow density > 1.2 people / square meter), and 20:00 - 8:00 as the "nighttime regular charging demand period" (density < 0.5 people / square meter).

[0073] 102. According to the demand distribution result output by the demand period division model, adjust the position of the edge computing device deployed in the target area so that the service range of the edge computing device moves in accordance with the peak area of the pedestrian flow density;

[0074] In this step, the edge computing device is a distributed computing node deployed in the target area, with real-time data processing and communication capabilities, and is used to dynamically adjust the service range to adapt to the spatial movement of the peak area of the pedestrian flow density.

[0075] In the embodiment of the present application, based on the dynamic heat map output by the demand period division model, the movement trajectory coordinate sequence of the peak area of the pedestrian flow density is extracted. A multi-objective optimization problem is constructed by covering radius constraint and network delay constraint, and a heuristic search algorithm is used to solve the device migration path. During the migration process, the signal strength and network topology status of adjacent devices are monitored in real time, and the shortest delay communication link is dynamically established to ensure that the data interaction meets the real-time requirements. Finally, the optimal position set of the edge computing device and its corresponding service coverage range are output.

[0076] For example, continuing with the previous example, when the midday peak flow of people moves from the office area on the west side of the commercial and residential complex to the dining area on the east side, the edge computing device moves 120 meters along a preset path to the center point of the new peak and establishes a two-hop communication link with adjacent devices. After the adjustment, the population density coverage rate within the device coverage area increases from 58% to 89%, and the end-to-end data transmission delay decreases from 68 ms to 41 ms.

[0077] 103. Based on the type of charging demand identified in the location adjustment result, control the multi-port wireless charging system to switch the charging power output mode, where the charging power output mode corresponds to the time periods of the fast charging demand and the normal charging demand;

[0078] In this step, the charging power output mode is a power configuration scheme dynamically adjusted by the multi-port wireless charging system according to the demand type, including a high-power fast charging mode and a low-power normal mode, and differential output is achieved through electromagnetic coupling parameter control.

[0079] In the embodiment of the present application, based on the distribution of demand types identified within the coverage area of the edge device, a priority weight is assigned to each charging port to switch the charging power output mode: the operating frequency band of the coil is adjusted through a resonant frequency adaptive matching algorithm (for example, a 6.78 MHz narrowband mode is used for fast charging, and a 13.56 MHz broadband mode is used for normal charging), while the physical spacing of the power transmission coil is optimized (a 10 cm tight coupling is used for the fast charging mode, and a 30 cm loose coupling is used for the normal mode), and an impedance matching network is used to compensate in real time for the energy loss caused by device displacement to ensure the stability of power output.

[0080] For example, continuing with the previous example, 82% of the fast charging demand is detected at 6 charging ports in the dining area on the east side of the commercial and residential complex. The resonant frequency is locked at 6.78 MHz, the coil spacing is adjusted to 10 cm, and the output power is increased to 120 kW; while the ports in the residential area on the north side are switched to the 13.56 MHz broadband mode, the spacing is increased to 30 cm, and the power is stabilized at 22 kW.

[0081] 104. Combine the network layout data after the position adjustment of the edge computing device with the information corresponding to the power output mode of the multi-port wireless charging system to generate a set of candidate charging pile layout positions;

[0082] In this step, the set of candidate charging pile layout positions is a set of candidate positions generated by combining the device layout data with the power mode information, and it needs to meet the indicators of daytime service efficiency and nighttime device utilization rate at the same time.

[0083] In the embodiments of the present application, the coverage area of edge computing devices is discretized into high-precision geographical grids, and the daytime service efficiency scores of each grid (based on pedestrian flow density, charging waiting time, and device load rate) are calculated. Synchronously analyze the night-time power output curve of the wireless charging system, and screen out the output areas with utilization rates higher than the average level. Exclude prohibited construction areas (such as fire lanes and green belts) through spatial overlay and conflict detection, and finally generate a set of candidate charging pile layout positions covering the daytime high-efficiency areas and night-time high-utilization areas.

[0084] For example, continuing with the above example, 35 candidate grids are screened out on the southeast side of the commercial and residential complex. Among them, 12 grids simultaneously meet the daytime efficiency score > 8.0 (full score 10) and night-time utilization rate > 70%. After excluding the occupied road areas, 28 positions are retained to form a candidate set, and the distance between each position is ≥ 8 meters and ≤ 25 meters.

[0085] 105. Perform distance verification on each position in the set of candidate charging pile layout positions, and screen out the target charging pile layout scheme that meets the preset safety standards and matches the demand distribution law of the demand period division model.

[0086] In this step, the safety distance verification of the underground pipe network is a verification step to detect whether the straight-line distance between the candidate position and the underground gas pipeline and the power pipe gallery meets the construction safety standards.

[0087] In the embodiments of the present application, the three-dimensional coordinate data of the underground pipe network is converted into a spatial risk layer, and the Euclidean distance between each candidate position and the nearest risk source (gas pipe, cable well) is calculated. Apply a penalty weight to the candidate positions with a distance less than the safety threshold, and at the same time, perform a comprehensive score in combination with the matching degree of the demand distribution law (such as the similarity of the historical pedestrian flow density curve). Screen out the final target charging pile layout scheme through multi-dimensional weighted ranking.

[0088] For example, continuing with the above example, among the 28 candidate positions, 9 positions with a distance of less than 2 meters from the gas pipeline are excluded, and 6 positions have a demand matching degree lower than the standard. Finally, 13 positions are selected to form the target charging pile layout scheme, among which 8 are located in the core area of the dining area and 5 are near the entrances and exits of residential areas.

[0089] Steps 101 - 105 realize the full-cycle intelligent decision-making of the charging pile layout in the urban mixed function area by dynamically perceiving the change of pedestrian flow density, real-time adjusting the edge computing resources, adaptively optimizing the charging power output, collaboratively screening candidate positions, and strictly verifying safety. In complex scenarios such as commercial and residential complexes, it significantly improves the daytime charging service response speed and night-time device resource utilization rate, effectively avoids construction safety hazards, and forms a closed-loop optimization system driven by demand, coordinated by resources, and controllable in safety.

[0090] In order to further improve the collaborative optimization ability of the charging pile layout scheme between daytime efficiency and nighttime utilization rate, and to solve the problems of rigid spatial resource allocation and fragmented time period demand response in the existing technology, this application constructs a candidate location generation mechanism that couples spatio-temporal efficiency by integrating edge computing dynamic layout data and the power characteristics of a wireless charging system. In some embodiments, generating a set of candidate charging pile layout positions by combining the network layout data after position adjustment of the edge computing device and the power output mode information of the multi-port wireless charging system, includes:

[0091] 201. Extract the network layout data after position adjustment of the edge computing device, and identify continuous spatial regions that meet the requirements of daytime charging service efficiency;

[0092] In step 201, the continuous spatial region refers to the set of physical spaces within the coverage range of the edge computing device that meet the requirements of daytime charging service efficiency, and needs to include both the peak point of pedestrian flow density and the minimum service radius constraint.

[0093] In the embodiments of this application, based on the network topology data after the migration of the edge computing device, an improved spatial clustering algorithm (such as a density-based DBSCAN variant) is used to rasterize the coverage area. First, the device service radius is discretized into 50cm×50cm grid cells, and the daytime charging service efficiency index of each grid (comprehensively generated by the weighted value of pedestrian flow density, the attenuation coefficient of charging request response time, and the device load balance degree) is calculated. Discrete noise points are eliminated through a multi-scale morphological filtering algorithm, and grid clusters with high efficiency and spatial continuity are retained. Finally, the region growing algorithm is used to merge adjacent high-efficiency grids to form a continuous spatial region that meets the minimum service area threshold.

[0094] 202. Synchronously obtain the power output mode information of the multi-port wireless charging system, and mark the output regions where the power utilization rate continuously exceeds the average level during the nighttime period;

[0095] In step 202, the output region is the effective coverage range where the power utilization rate of the multi-port wireless charging system continuously exceeds the average level during the nighttime period, and is the spatial intersection of the electromagnetic field strength distribution of the power transmission coil and the hot zone of conventional charging demand.

[0096] In the embodiments of the present application, the historical power output curves of each port are collected by a wireless charging control module, and the time series piecewise aggregate approximation (PAA) algorithm is used to extract the stable high-utilization period at night (such as 22:00-6:00). A coil coverage intensity heat map is constructed based on the electromagnetic field finite element simulation data, and the spatial distribution of the conventional charging demand hot zone (from the demand period division model) is superimposed. Spatial convolution operation is used to fuse the features of the heat map and the demand distribution map, and the grid set with the electromagnetic field strength value greater than the critical strength and the demand density higher than the regional average is screened out and marked as the high-utilization output area.

[0097] 203. Perform a geospatial overlay of the continuous spatial region and the output region, and screen out the candidate layout range that simultaneously includes the boundary of the daytime efficiency region and the core area of the nighttime utilization rate.

[0098] In step 203, the candidate layout range is the optimized interval generated by spatially overlaying the continuous spatial region and the output region, and it needs to simultaneously include the boundary constraint of the daytime efficiency region and the coverage range of the core area of the nighttime utilization rate.

[0099] In the embodiments of the present application, the grid data of the continuous spatial region and the output region are converted into vector polygons, and the topological overlay algorithm (such as the intersection operation in Boolean operations) is used to obtain the overlapping region. The geometric contour line of the daytime efficiency region is identified by the boundary extraction algorithm, and a spatial constraint network is constructed in combination with Delaunay Triangulation. Each sub-region within the overlapping region is scored with multiple indicators (60% weight for daytime efficiency and 40% weight for nighttime utilization rate), and the non-dominated sorting genetic algorithm (NSGA-II) is used to screen the Pareto optimal solution set to generate a candidate layout range that takes into account the dual-period indicators.

[0100] 204. Based on the candidate layout range, perform a spatial priority ranking on the deployable region according to the preset charging pile spacing rule, and generate a set of candidate charging pile layout positions.

[0101] In step 204, the spatial priority ranking is to perform a hierarchical evaluation on the deployable region within the candidate layout range according to the preset charging pile spacing rule, and preferentially select the position with the optimal comprehensive efficiency and meeting the engineering constraints.

[0102] In the embodiments of the present application, a spatial optimization model with constraint conditions is constructed within the candidate layout range. First, an improved ant colony algorithm (introducing a dynamic pheromone evaporation mechanism) is used to traverse all feasible positions, and the coverage redundancy of adjacent charging piles at each position is calculated (the weighted sum of the reciprocals of the distances to adjacent positions). The geographical accessibility of the position (the length of the shortest arrival path generated based on the path planning algorithm) and the grid access cost (converted according to the distance from the substation facilities) are evaluated synchronously. The above indicators are jointly optimized through a multi-objective particle swarm optimization algorithm (MOPSO), and a set of candidate charging pile layout positions sorted in descending order of comprehensive scores is output.

[0103] The following is a specific example:

[0104] In the underground parking lot on the first basement floor of a subway superstructure property complex, during the daytime commuting period (7:00 - 19:00), the peak pedestrian flow density in the west office area reaches 2.1 people / m², and during the nighttime living period (20:00 - 6:00), the charging demand ratio in the east residential area exceeds 75%. In step 201, the coverage data of the migrated edge computing devices is extracted to identify the continuous spatial area in the west (with an area of 1200 m², containing 6 pedestrian flow peak points, and a service radius ≥ 15 m); in step 202, the data of the wireless charging system is obtained synchronously to mark the high-utilization output area in the east at night (electromagnetic field strength > 3 A / m, demand density > 0.8 people / m²); through step 203, the candidate layout range in the north-south transition zone is screened out after spatial overlay (with an area of 800 m², daytime efficiency score > 7.5, and nighttime utilization rate > 65%); in step 204, 32 candidate positions are generated according to the spacing rule, among which 18 are located in the core corridor area (spacing 12 - 20 m, grid access distance < 50 m), generating a set of candidate charging pile layout positions.

[0105] Steps 201 - 204 achieve the dynamic balance between the daytime efficiency and nighttime utilization rate of the charging pile layout through the coordination of spatio-temporal clustering, electromagnetic field fusion, topological overlay, and multi-objective optimization technologies. In the scenario of urban mixed-functional areas, it significantly improves the spatio-temporal adaptability of charging resources, reduces the equipment idle rate and the risk of grid fluctuations, and forms an overall process optimization ability from data fusion, spatial analysis to project implementation.

[0106] In order to further improve the safety of the charging pile layout scheme and the matching accuracy of demand patterns, and solve the problems of the separation between safety verification and dynamic demand adaptation and the high cost of manual correction in the existing technology, the present application constructs a multi-dimensional linkage safety screening and dynamic adaptation mechanism by integrating three-dimensional data of underground pipe networks, the spatial distribution of demand hot zones, and historical pedestrian flow fluctuation rules. In some embodiments, the distance verification of each position in the set of candidate charging pile layout positions to screen out the target charging pile layout scheme that meets the preset safety standards and matches the demand distribution rules of the demand period division model includes:

[0107] 301. Obtain the spatial distance between each location in the set of candidate charging pile layout positions and the three-dimensional coordinate data of the underground pipe network, and filter out the subset in which the straight-line distances from each location to the gas pipeline and the power pipe gallery are both greater than the preset safety distance.

[0108] In step 301, the preset safety distance is the minimum straight-line distance threshold between the charging pile layout position and the underground gas pipeline, power pipe gallery and other infrastructure set in advance, and it needs to comply with the municipal construction safety specifications.

[0109] In the embodiment of the present application, the three-dimensional point cloud data of the underground pipe network is loaded through a three-dimensional geographic information system (GIS) engine, and the candidate position coordinates are converted into a spatial rectangular coordinate system. The improved K-Nearest Neighbors (K = 5) algorithm is used to retrieve the nearest gas pipeline nodes and the central points of the cross-sections of the power pipe galleries around each location, and the minimum Euclidean distance is calculated. The Monte Carlo risk simulation method is introduced to estimate the probability density of the distance distribution, and the positions with a safety probability lower than the confidence interval (such as 95%) are excluded, and finally a subset containing all the positions with qualified safety distances is generated.

[0110] 302. Based on the spatial distribution of the fast charging demand hot spots and the conventional charging demand hot spots marked in the demand period division model, calculate the area ratio of the subset covering the two types of demand hot spots, and retain the adapted positions where the area ratio simultaneously meets the lower limits of the daytime fast demand and the nighttime conventional demand.

[0111] In step 302, the area ratio is the spatial coverage area ratio of the candidate position subset to the fast charging demand hot spots and the conventional charging demand hot spots, and it needs to simultaneously meet the lower limit thresholds of the daytime and nighttime coverage.

[0112] In the embodiment of the present application, the vector boundary data of the fast charging demand hot spots and the conventional charging demand hot spots is rasterized (resolution 0.5m × 0.5m), and the region growing algorithm is used to perform spatial overlay analysis on the candidate position subset. Count the number of grids covering the two types of hot spots in the buffer zone of each location, and calculate the area ratio (fast demand coverage ratio = number of grids covering the hot spots / total number of grids). The daytime and nighttime coverage lower limits are dynamically set through the adaptive threshold segmentation algorithm (Otsu variant), and the positions that meet both thresholds are retained. The remaining positions are subjected to spatial autocorrelation test (Moran's I index), and the isolated points are excluded.

[0113] 303. Verify the safety spacing of the underground pipe network for the adapted positions, exclude the abnormal positions whose spacing from the adjacent pipe network positions exceeds the preset spacing interval, and generate an intermediate layout plan set.

[0114] In step 303, the intermediate layout plan set is a set of temporary layout plans generated after passing through multi-level safety distance verification, and it is necessary to further screen the final plan in combination with the dynamic demand law.

[0115] In the embodiment of the present application, based on the three-dimensional pipe network topological relationship model, an implicit surface (Implicit Surface) is constructed to represent the safety envelope of the pipe gallery. The ray casting algorithm (Ray Casting) is used to calculate the shortest distance from the adaptation position to the surface of the envelope. If the distance is less than the minimum distance or greater than the maximum distance, it is marked as abnormal. The hidden Markov model (HMM) is introduced to analyze the spatial aggregation pattern of abnormal positions and identify systematic risk areas (such as pipeline intersections). Finally, a set of intermediate layout plans constrained by multi-level distances is output.

[0116] 304. Perform a safety assessment according to the historical period pedestrian flow density curve in the intermediate layout plan set, and perform a similarity matching between the inspection result and the demand distribution law of the demand period division model, and screen out the target charging pile layout plan that meets the preset safety standard and matches the demand distribution law.

[0117] In step 304, the safety assessment combines the historical pedestrian flow density curve and the demand distribution law to verify the matching degree between the intermediate plan and the dynamic demand fluctuation.

[0118] In the embodiment of the present application, the historical pedestrian flow density time series (sampling frequency 15 minutes) of each position in the intermediate plan is extracted, and the dynamic time warping (DTW) algorithm is used to calculate its similarity distance from the reference curve of the demand period division model. The similarity distance matrix is divided into a high matching degree cluster and a low matching degree cluster by spectral clustering (Spectral Clustering). Spatial kernel density estimation (Kernel Density Estimation) is performed on the positions within the high matching degree cluster, and the density peak points are screened to generate the target charging pile layout plan.

[0119] The following is a specific example:

[0120] Underground parking lot on the first basement floor of a subway-integrated property complex. During the day (7:00 - 19:00), a fast-charging demand hot zone (with an area of 600 ㎡) is formed in the west office area, and at night (20:00 - 6:00), a conventional demand hot zone (with an area of 450 ㎡) is formed in the east residential area. The set of candidate layout positions contains 50 points. After screening in step 301, 32 subsets that include all positions meeting the safety distance standards are retained (distance from gas pipelines > 2.5m, distance from power pipe galleries > 1.8m). The area ratio calculation in step 302 shows that 18 of these positions cover both the day hot zone area ≥ 55% and the night hot zone area ≥ 40%. In step 303, 4 positions with abnormal spacing (close to drainage manholes, spacing < 0.8m) are further removed, generating a set of 14 intermediate layout schemes. In step 304, based on half-year historical data, 8 target positions (DTW similarity > 0.75, kernel density peak > 1.2) are selected and distributed in the west passage and the east transition area, with a spacing of 12 - 22 meters, generating the target charging pile layout scheme.

[0121] Steps 301 - 304 achieve an accurate balance between the charging pile layout scheme and the adaptation to dynamic demands under the safety constraints of underground pipe networks through three-dimensional space distance screening, dynamic area ratio calculation, multi-level safety distance verification, and historical pattern matching evaluation. In the scenario of urban mixed-functional areas, it significantly improves construction safety and demand response consistency, reduces operation and maintenance risks and resource misallocation rates, and forms a full-link closed-loop decision-making ability from geometric constraints, spatial analysis to temporal sequence matching.

[0122] In order to further improve the dynamic response ability and network transmission stability of edge computing device deployment, and solve the problem of insufficient real-time demand response caused by high device migration latency and rigid network topologies in the existing technology, this application constructs an edge computing resource scheduling system that adapts to the peak movement of the flow of people through spatio-temporal trajectory prediction, dynamic location optimization, network reconstruction, and closed-loop feedback mechanisms. In some embodiments, adjusting the positions of the edge computing devices deployed in the target area according to the demand distribution result output by the demand period division model includes:

[0123] 401. Analyze the demand distribution result output by the demand period division model, extract the coordinate set of high-demand areas in the target area during the current period, and determine the movement trajectory of the peak area of the flow density of people according to the spatio-temporal distribution characteristics of the coordinate set of high-demand areas;

[0124] In step 401, the coordinate set of high-demand areas is a set of geographical locations in the target area where the flow density of people exceeds a preset threshold during the current period, and is used to represent the charging demand aggregation area.

[0125] In the embodiments of the present application, a multi-scale analysis is performed on the dynamic distribution results output by the demand period division model through a spatio-temporal density clustering algorithm (such as the improved OPTICS algorithm) to extract core clustering clusters that meet the density threshold. The time series piecewise linear representation (PLR) algorithm is used to compress the spatio-temporal coordinate sequence to identify the center of gravity drift direction of adjacent period clustering clusters. A state transition probability matrix is established based on the hidden Markov model (HMM) to decode the continuous movement path of the peak region and generate a movement trajectory containing timestamps and spatial coordinates.

[0126] 402. Based on the central positions of the peak regions of each time segment in the movement trajectory, calculate the target deployment position set of the edge computing device, where the straight-line distance between each target position in the target deployment position set and the center of the peak region of the corresponding time segment does not exceed a preset coverage radius;

[0127] In step 402, the target deployment position set is the optimal position set to which the edge computing device needs to be migrated, ensuring that the distance between each position and the center of the peak region of the corresponding period does not exceed the preset coverage radius.

[0128] In the embodiments of the present application, based on the spatio-temporal coordinate points in the movement trajectory sequence, a position optimization model is constructed using a reinforcement learning framework (such as Q-Learning). The state space is defined as the Euclidean distance difference between the real-time coordinates of the peak region and the current position of the device, and the action space is the device migration direction (8-neighborhood discretization) and step size (50m / 100m). The reward function comprehensively considers the coverage gain (the increase in the pedestrian flow density within the service range) and the migration cost (energy consumption + network reconstruction overhead). The Q-value table is iteratively updated through the ε-greedy strategy to output the target deployment position set that satisfies the coverage radius constraint and maximizes the cumulative reward.

[0129] 403. Generate a device migration instruction according to the target deployment position set, drive the edge computing device to migrate to the target position according to the device migration instruction, and establish a communication network with adjacent devices during the migration process to control the end-to-end transmission delay between nodes in the communication network to be lower than a preset maximum value;

[0130] In step 403, the device migration instruction is a control instruction set for driving the edge computing device to migrate to the target position according to a preset path, including the migration path, speed, and network reconstruction parameters.

[0131] In the embodiment of the present application, the target deployment location set is input into a path planning algorithm (such as an improved A* algorithm) to generate a device migration instruction based on the optimal obstacle-avoiding migration path (avoiding fixed obstacles such as fire corridors and load-bearing columns). During the migration process, the distributed consensus protocol (a variant of the Raft algorithm) is used to negotiate the priority of establishing communication links with adjacent devices, and a minimum spanning tree (MST) network topology is dynamically constructed. The link-state routing protocol (an improved OSPF) is used to calculate the shortest transmission path between nodes in real time, and the traffic shaping technology (Token Bucket algorithm) is used to limit the single-hop delay to ensure that the end-to-end delay is lower than a preset maximum value.

[0132] 404. Obtain the updated coordinate set of the peak area through the communication network. When it is detected that the coverage overlap rate between the updated coordinate set and the target deployment location set is lower than a preset tolerance threshold, re-execute the calculation of the target deployment location set based on the updated coordinate set, and synchronously adjust the device migration instruction.

[0133] In step 404, the coverage overlap rate is the ratio of the intersection area of the coverage areas of the updated coordinate set and the target deployment location set to the coverage area of the original location set, and is used to quantify the degree of trajectory deviation.

[0134] In the embodiment of the present application, the updated coordinate set of the peak area is collected in real time through the communication network, and the Jaccard similarity coefficient is used to calculate its coverage overlap rate with the target location set. If the overlap rate is lower than the tolerance threshold, an incremental trajectory prediction process is triggered: the Kalman filter algorithm is used to correct the mobile trajectory prediction error, and steps 401-402 are re-executed to generate a new target deployment location set. The receding horizon control strategy is used to dynamically adjust the migration instruction to ensure a smooth transition of the device migration path and minimize the network topology reconstruction overhead.

[0135] The following is a specific example:

[0136] The underground parking lot on the first basement floor of a subway-integrated property complex has a peak flow area during the day (7:00 - 19:00) that cyclically moves from the west security checkpoint to the central commercial area following the commuting tide pattern. Step 401 analyzes the demand distribution data, extracts the high-demand coordinate set (west coordinate cluster A, density > 2 people / ㎡) during peak hours (8:00 - 9:30), and generates a movement trajectory (west → northeast → eastward drift) through HMM decoding; Step 402 calculates the target location set (locations P1 - P5) through the Q-Learning model, with a coverage radius set at 30 meters, ensuring that the distance from each location to the trajectory center point is ≤ 25 meters; Step 403 generates a migration path (west P1 → northeast P3 → east P5) through the A* algorithm, and establishes a three-hop MST network with adjacent devices during the migration process, with the end-to-end delay stabilized below 45 ms; In Step 404, at noon, it is detected that the updated coordinate set has moved 200 meters eastward (due to a temporary commercial activity), and the coverage overlap rate drops to 40%, triggering trajectory correction and regenerating the target deployment location set (new locations P6 - P8). After the devices are migrated to the new locations, the overlap rate resumes to 82%.

[0137] Steps 401 - 404 achieve real-time tracking and adaptive coverage of the peak flow area by edge computing devices through the collaboration of spatio-temporal clustering, reinforcement learning, distributed network optimization, and rolling horizon control technologies. In the scenario of urban mixed-functional areas, it significantly improves the timeliness of charging demand response, reduces network transmission delay and device migration energy consumption, forms a closed-loop optimization ability from trajectory prediction, resource scheduling to dynamic correction, and ensures service continuity in complex scenarios.

[0138] In order to further improve the power allocation accuracy and adaptive ability of the wireless charging system in dynamic demand scenarios, and solve the problems of lagging power mode switching, coexistence of device vacancy and overload in the existing technology, this application constructs a demand-driven wireless charging power control system through demand type recognition, priority dynamic configuration, electromagnetic parameter optimization, and closed-loop feedback mechanism. In some embodiments, controlling the multi-port wireless charging system to switch the charging power output mode based on the charging demand type identified in the location adjustment result includes:

[0139] 501. Obtain the charging demand type marked in the location adjustment result, where the charging demand type includes a first type of demand signal and a second type of demand signal corresponding to the fast charging demand and the conventional charging demand respectively;

[0140] In Step 501, the charging demand type is the category of the charging demand marked according to the demand period division model, including a first type of demand signal corresponding to the fast charging demand and a second type of demand signal corresponding to the conventional charging demand.

[0141] In the embodiments of the present application, location adjustment result data uploaded by an edge computing device is used to extract the charging demand type tags annotated in the spatio-temporal tag matrix. A spatio-temporal clustering algorithm (such as the improved ST-DBSCAN) is used to perform spatial aggregation on the demand signals, separating the high-density fast charging demand clusters (the first type of signals) from the low-density conventional demand clusters (the second type of signals), and eliminating environmental noise interference based on the Blind Source Separation (BSS) technology.

[0142] 502. According to the spatial distribution density of the charging demand type, a priority matching rule is configured for each charging port of the multi-port wireless charging system, and the priority of the charging port in the coverage area of the first type of demand signal is higher than that of the second type of demand signal;

[0143] In step 502, the priority matching rule is a service priority policy assigned to the wireless charging ports, ensuring that the priority of the ports in the coverage area of the first type of demand signal is higher than that of the second type of demand signal area.

[0144] In the embodiments of the present application, based on the heat map of the spatial distribution density of the demand type, a spatial convolution kernel (Gaussian Kernel) is used to calculate the demand density integral value within the coverage range of each charging port. A multi-port collaborative optimization model is constructed through a dynamic game theory framework (Nash Bargaining Solution), and the port utility function is defined as the weighted difference between the demand density integral value and the interference coefficient of adjacent ports. The Alternating Direction Method of Multipliers (ADMM) is used to solve the Nash equilibrium point, generating a priority weight matrix for configuring the priority matching rule, where the priority weight coefficient of the ports in the first type of signal area is not less than 1.5 times that of the second type of area.

[0145] 503. Based on the priority matching rule, adjust the electromagnetic coupling parameter combinations of each charging port in the multi-port wireless charging system so that the output power range of the high-priority charging ports adapts to the fast charging demand, and the output power range of the low-priority charging ports adapts to the conventional charging demand. The electromagnetic coupling parameter combinations include the resonant frequency matching range and the power transmission coil spacing;

[0146] In step 503, the electromagnetic coupling parameter combination is a set of working parameters of each port in the multi-port wireless charging system, including the resonant frequency matching range and the power transmission coil spacing, for controlling the output power mode.

[0147] In the embodiments of the present application, the electromagnetic coupling parameter combination is adjusted according to the priority matching rule. A narrowband resonant frequency (such as 6.78 MHz ± 0.5 MHz) and a small-spacing coil layout (≤ 15 cm) are configured for the high-priority port, and a dynamic impedance matching network (real-time calibration based on the Smith chart) is used to optimize the energy transfer efficiency. The low-priority port is switched to a broadband resonant frequency (13.56 MHz ± 2 MHz) and a large-spacing coil layout (≥ 30 cm). The electromagnetic field uniformity of the coil array is optimized by the genetic algorithm (NSGA-II), and a parameter fitness surface is constructed using the finite element simulation data to obtain the Pareto optimal solution.

[0148] 504. Through the electromagnetic coupling state feedback data of the multi-port wireless charging system, periodically detect the fitness of the actual output power of each charging port and the priority matching rule. If it is detected that the fitness is lower than the requirement of the matching rule, regenerate the electromagnetic coupling parameter combination and update the priority matching rule.

[0149] In step 504, the fitness is the degree of compliance between the actual output power of the charging port and the target power range required by the priority matching rule, and is used to quantify the effectiveness of parameter configuration.

[0150] In the embodiments of the present application, the real-time output power, efficiency, and coil temperature data of each port are collected by the wireless charging control module, and the covariance analysis (ANCOVA) is used to calculate the deviation degree between the actual output and the target power. If the deviation degree exceeds the preset threshold, trigger the parameter re-optimization process: predict the change trend of the demand density based on the Kalman filter algorithm, and re-execute steps 502 - 503 to generate the updated priority rule and parameter combination. The rolling horizon optimization strategy is used to achieve dynamic fine-tuning of the parameters to ensure continuous adaptation to demand fluctuations.

[0151] The following is a specific example:

[0152] The underground parking lot of a commercial and residential complex is divided into a west office area (with intensive daytime fast charging demand) and an east residential area (dominated by nighttime regular demand). In step 501, after the edge devices are migrated, the west coordinates (X1, Y1) to (X5, Y5) are marked as the first type of demand signal (density > 1.8 people / m²), and the east coordinates (X6, Y6) to (X10, Y10) are the second type of signal (density < 0.6 people / m²); the Gaussian kernel convolution calculation in step 502 shows that the demand density integral value of the west ports P1 - P3 reaches 4.2, and that of the east ports P4 - P6 is 1.5. The game model assigns a priority weight of 2.0 to P1 - P3 and 1.3 to P4 - P6; in step 503, P1 - P3 are configured with a narrow - band resonance of 6.78 MHz and a coil spacing of 12 cm, and the output power is increased to 120 kW; P4 - P6 are switched to a broadband of 13.56 MHz and a spacing of 35 cm, and the power is stabilized at 25 kW; in step 504, at noon, the actual output power of P2 is only 95 kW (target 120 kW). Covariance analysis shows insufficient fitness. After re - optimization, its resonance frequency is adjusted to 6.80 MHz, and the power is restored to 118 kW.

[0153] Steps 501 - 504 achieve high - precision adaptation of wireless charging power output to dynamic demand through demand signal separation, game optimization, electromagnetic parameter dynamic matching, and closed - loop feedback control. In the scenario of urban mixed - function areas, it significantly improves the fast - charging demand response speed and the utilization rate of conventional charging devices, reduces energy loss and the risk of equipment overheating, and forms an all - link adaptive ability from demand recognition, rule configuration to parameter closed - loop optimization.

[0154] In order to improve the spatio - temporal accuracy and dynamic adaptation ability of charging demand time - period division, and solve the problem of rigid time - period division caused by complex pedestrian flow fluctuations in the existing model in the mixed - function area scenario, this application constructs a dynamically evolving demand time - period division system through spatio - temporal grid analysis, density pattern recognition, overlap degree optimization, and model self - correction mechanism. In some embodiments, the method for generating a demand time - period division model based on the spatio - temporal variation law of pedestrian flow density in the mobile terminal communication data includes:

[0155] 601. Extract the spatial coordinates and timestamps of terminal devices in the mobile terminal communication data, and construct a spatio - temporal distribution sequence of pedestrian flow density with geographical grids as units;

[0156] In step 601, the spatio - temporal distribution sequence of pedestrian flow density is a data sequence of the distribution density of terminal devices statistically calculated by time window with geographical grids as units, which is used to quantify the aggregation characteristics of pedestrian flow in the spatio - temporal dimension.

[0157] In the embodiments of the present application, anonymous signaling data collected by a mobile terminal communication base station is used to extract the device MAC address, timestamp, and longitude and latitude coordinates. The time series Piecewise Aggregate Approximation (PAA) algorithm is used to divide the original data stream into equal-length time periods (such as 15 minutes), and spatial grid division (the grid size is dynamically adapted to the area of the region) is performed on the coordinate points within each time period. Based on the Kriging Interpolation algorithm, sparse grid data is complemented to generate a spatio-temporal distribution sequence of pedestrian flow density containing grid center coordinates, pedestrian flow density values, and time tags. The sequence data is updated through a sliding window mechanism to ensure real-time performance.

[0158] 602. Perform pattern recognition on the pedestrian flow density fluctuation characteristics within each geographical grid in the spatio-temporal distribution sequence of pedestrian flow density, and extract the set of grids with short-term high-density aggregation characteristics during the daytime period as the fast charging demand candidate areas, and the set of grids with continuous medium and low density distribution during the nighttime period as the conventional charging demand candidate areas;

[0159] In step 602, the fast charging demand candidate areas are the set of grids where the pedestrian flow density surges short-term and the aggregation duration is less than a preset threshold during the daytime period. The conventional charging demand candidate areas are the set of grids where the pedestrian flow density is stably maintained at a medium and low level and the duration exceeds a preset threshold during the nighttime period.

[0160] In the embodiments of the present application, for each grid cell in the spatio-temporal distribution sequence, the Morphological Clustering algorithm is used to identify the density fluctuation pattern. For the daytime period, the Dynamic Time Warping (DTW) algorithm is used to match short-term spike waveforms (duration ≤ 2 hours, peak density ≥ 1.5 people / ㎡) to screen out the fast demand candidate areas; for the nighttime period, the Autoregressive Integrated Moving Average model (ARIMA) is used to detect the stationarity index to screen out the conventional demand candidate areas with continuous medium and low density (0.3 - 0.8 people / ㎡) and variance lower than the threshold. Discrete noise grids are removed through spatial connectivity analysis, and the vector boundary data of the candidate areas is output.

[0161] 603. Based on the spatio-temporal overlap analysis of the fast charging demand candidate areas and the conventional charging demand candidate areas, the candidate areas with spatial coverage area exceeding the overlap upper limit in adjacent time segments are merged into demand period division units, and each division unit is labeled with the corresponding charging demand type label;

[0162] In step 603, the demand period division units are continuous spatio-temporal blocks generated by merging spatio-temporally overlapping candidate areas, and are labeled as the dominant type of fast or conventional charging demand.

[0163] In the embodiments of the present application, the spatio-temporal coordinates of fast and regular candidate areas are mapped to a four-dimensional tensor space (longitude, latitude, start and end time, density level), and the community discovery algorithm (Louvain Method) in graph theory is used to identify candidate area clusters with high overlap. The spatio-temporal overlap is defined as the proportion of the intersection of the spatial coverage areas of candidate areas in adjacent time periods. If the overlap exceeds 75%, they are merged into demand time period division units, and the dominant charging demand type is labeled for each unit through the Label Propagation algorithm.

[0164] 604. According to the label distribution law of the demand time period division units in the historical period, correct the division granularity of the geographical grid and the decision threshold of the spatio-temporal overlap analysis, and generate a demand time period division model adapted to the characteristics of the change in the flow of people in the target area.

[0165] In step 604, the demand time period division model is a decision model generated after dynamically correcting the grid granularity and overlap threshold based on historical data, and is used to predict the demand time period distribution in the target area.

[0166] In the embodiments of the present application, the label distribution data of the division units in the historical period is extracted, and the Bayesian Optimization framework is used to adjust the grid granularity and overlap threshold. The prediction accuracy rate (F1-score) of the parameter combination is evaluated through cross-validation, and the Pareto optimal solution is selected to update the model parameters. The Long Short-Term Memory network (LSTM) is used to model the temporal dependence of the corrected parameters, and finally a demand time period division model adaptable to the dynamic change of the flow of people is output.

[0167] The following is a specific example:

[0168] For the underground second-floor parking lot of a property complex above a subway station, obvious daytime commuting (a sharp increase in the flow of people at the west entrance from 7:00 to 10:00) and nighttime residence (stable demand in the east residential area from 20:00 to 6:00) characteristics are presented on weekdays. In step 601, the mobile signaling data is divided into 15-minute windows, and a spatio-temporal sequence of a 50m×50m grid is constructed. The density of the west grid G12 suddenly increases from 0.5 person / m² to 2.3 person / m² from 8:00 to 9:00; in step 602, the MCL algorithm identifies G12 as a fast candidate area (the peak lasts for 55 minutes), and the east grids E7-E9 are marked as regular candidate areas (the density is 0.4-0.7 person / m² for 8 hours); in step 603, the Louvain algorithm merges the adjacent time period G12-G15 candidate areas (the overlap is 83%) to generate the west division unit U1 (dominated by fast), and merges E7-E9 into the unit U2 (dominated by regular); in step 604, the grid granularity is reduced to 30m×30m through Bayesian optimization, the overlap threshold is increased to 85%, and the accuracy rate of the LSTM prediction model is increased to 92%.

[0169] Steps 601-604 achieve high-precision dynamic modeling of demand period division through spatio-temporal grid analysis, density pattern clustering, community discovery optimization, and parameter self-correction technology. In the scenario of urban mixed-functional areas, it significantly improves the adaptability of period division to complex human flow fluctuations, reduces the resource mismatch rate, and forms an all-round optimization ability from data quantification, pattern mining to model self-evolution.

[0170] In order to further improve the network stability and real-time performance during the migration of edge computing devices, and solve the problems of communication interruption, topology rigidity, and delay fluctuation caused by device movement in the prior art, this application constructs a highly reliable edge computing network through path planning optimization, dynamic node selection, adaptive adjustment of network structure, and delay closed-loop control mechanism. In some embodiments, generating a device migration instruction according to the target deployment location set, driving the edge computing device to migrate to the target location according to the device migration instruction, and establishing a communication network with adjacent devices during the migration process, and controlling the end-to-end transmission delay between nodes in the communication network to be lower than a preset maximum value, includes:

[0171] 701. Generate a device migration instruction including a migration path and a migration speed according to the relative distance between each target location in the target deployment location set and the location of the current edge computing device;

[0172] In step 701, the device migration instruction is a control instruction set including the migration path and speed of the edge computing device, which is used to guide the device to migrate from the current location to the target location.

[0173] In the embodiments of this application, based on the relative distance matrix between the target location set and the current device location, the multi-objective genetic algorithm (NSGA-II) is used to optimize the migration path. The objective function is defined as minimizing the path length and maximizing obstacle avoidance (avoiding fixed obstacles such as fire channels and structural columns), and the constraint conditions include the maximum migration speed (≤1m / s) and acceleration limit (≤0.5m / s²). The dynamic programming algorithm (Dyna-Q) is used to predict the risk of sudden obstacles during the migration process, obtain alternative detour paths, and finally output a device migration instruction including the main path, alternative paths, and segmented speed curves.

[0174] 702. Drive the edge computing device to migrate to the target location according to the device migration instruction, detect the signal strength of adjacent edge computing devices during the migration process, and select adjacent devices with signal strength higher than a preset threshold as candidate nodes for the communication network;

[0175] In step 702, the candidate nodes are adjacent edge computing devices with signal strength higher than a preset threshold during the migration process, which are used to construct a temporary communication network.

[0176] In the embodiments of the present application, during the device migration process, the signal strength (RSSI) and signal-to-noise ratio (SNR) of surrounding devices are scanned in real time by the distributed radio frequency fingerprint acquisition module. The Kalman filter algorithm is used to eliminate environmental noise interference and dynamically update the signal strength threshold (initial -70dBm, adaptively adjusted according to the migration speed). Based on the fuzzy logic inference system, the node stability is evaluated (signal strength volatility < 15%, packet loss rate < 5%), and a list of high-reliability candidate nodes is selected. The availability of the nodes is confirmed through a lightweight consensus protocol (a variant of Paxos), and candidate nodes for the communication network are generated.

[0177] 703. Based on the location distribution and signal strength data of the candidate nodes, construct a star-shaped communication network topology centered on the edge computing device;

[0178] In step 703, the star-shaped communication network topology is a communication network structure with the edge computing device in migration as the central node and establishing single-hop connections with candidate nodes.

[0179] In the embodiments of the present application, based on the location distribution and signal strength data of the candidate nodes, the Closeness Centrality algorithm in graph theory is used to determine the central node to ensure that the maximum single-hop coverage radius ≤ 50 meters. The connection weights between nodes are optimized through the minimum spanning tree (Prim algorithm) (weighted based on the reciprocal of the signal strength and physical distance), and a low-latency backbone link is constructed. The time-division multiple access (TDMA) protocol is used to allocate communication time slots to avoid channel conflicts. Finally, a star-shaped communication network topology including the central node coordinates, connection relationships, and time slot tables is generated.

[0180] 704. Monitor the end-to-end transmission delay between each topology node in the star-shaped communication network topology. If it is detected that the end-to-end transmission delay exceeds the preset maximum value, reselect the candidate nodes and adjust the hop count distribution of the star-shaped communication network topology.

[0181] In step 704, the end-to-end transmission delay is the total time taken for data packet transmission between any two nodes in the star network topology, and it needs to be continuously monitored and controlled within the preset maximum value.

[0182] In the embodiments of the present application, the transmission delay data of each node is periodically collected through the link state routing protocol (improved OLSR), and the exponential weighted moving average (EWMA) algorithm is used to predict the delay trend. If it is detected that the delay exceeds the threshold (such as 100ms), trigger the topology reconstruction process: reselect candidate nodes based on the reinforcement learning framework (Q-Learning), and preferentially access devices with low load and high signal strength. The dynamic hop count constraint algorithm (DHC) is used to adjust the network level, reduce the maximum hop count from 2 hops to 1 hop, and limit burst traffic through the traffic shaping technology (Leaky Bucket).

[0183] The following is a specific example:

[0184] In the underground parking lot of a commercial and residential complex, during the day, edge computing devices need to be frequently relocated in the west office area to match the commuting tidal flow of people. In step 701, the target location set includes P1 (coordinates X = 120, Y = 80), P2 (X = 150, Y = 100). NSGA-II constructs the main path and generates a device relocation instruction (avoiding the B2 load-bearing column). The speed curve is segmented into 0.8 m / s (straight section) and 0.3 m / s (turning section); in step 702, during the relocation to P1, adjacent devices E3 (RSSI = -68 dBm) and E5 (RSSI = -72 dBm) are detected. Fuzzy logic selects E3 as a candidate node; in step 703, a star communication network topology is constructed with P1 as the center, connecting nodes E3 and E7 (single-hop distance ≤ 45 meters). TDMA allocates a time slot of 0.5 ms / node; in step 704, during the lunch peak, the delay from E3 to E7 is detected to increase to 110 ms. Q-Learning switches to the standby node E9 (RSSI = -65 dBm), and the hop count is adjusted to 1 hop, and the delay is reduced to 75 ms.

[0185] Steps 701-704 achieve high network reliability and low latency guarantee during the migration of edge computing devices through multi-objective path planning, fuzzy node selection, centrality network construction, and delay-driven topology optimization. In the scenario of urban mixed-functional areas, it significantly improves communication continuity in dynamic environments, reduces the risk of data transmission interruption, and forms an end-to-end closed-loop management capability from path control, node selection, to network self-healing.

[0186] In order to further improve the power output stability and energy efficiency adaptability of the wireless charging system in dynamic demand scenarios and solve the problems of rigid power configuration, coexistence of device overload and vacancy in the existing technology, this application constructs a demand-driven wireless charging power control system through spatial density quantization, parameter differential configuration, dynamic optimization, and closed-loop feedback mechanism. In some embodiments, adjusting the electromagnetic coupling parameter combinations of each charging port in the multi-port wireless charging system so that the output power range of the high-priority charging port adapts to the fast charging demand, and the output power range of the low-priority charging port adapts to the regular charging demand, includes:

[0187] 801. According to the spatial distribution of different priority charging ports marked in the priority matching rule, extract the spatial density parameter of the fast charging demand within the coverage area of the high-priority charging port;

[0188] In step 801, the spatial density parameter is the spatial distribution density quantization value of the fast charging demand within the coverage area of the high-priority charging port, which is used to characterize the demand intensity.

[0189] In the embodiments of the present application, for the high-priority port positions marked based on the priority matching rule, the kernel density estimation algorithm is used to perform spatial interpolation calculation on the fast charging demand points in the coverage area. A density heat map is generated through a Gaussian kernel function, and the geometric center coordinates and coverage radius of the peak area (density ≥ 1.5 people / m²) in the heat map are extracted. The spatial autocorrelation analysis (Moran's I index) is used to verify the spatial aggregation characteristics of the density distribution, and discrete noise points are removed. Finally, spatial density parameters including density values, center coordinates, and coverage ranges are output.

[0190] 802. Based on the spatial density parameters, configure a narrowband resonance frequency range and a small-spacing power transmission coil parameter combination for each high-priority charging port, so that the output power range of the high-priority charging port covers the power interval corresponding to the fast charging demand;

[0191] In step 802, the narrowband resonance frequency range and the small-spacing power transmission coil parameter combination are electromagnetic coupling parameters set to adapt to the high-power fast charging demand, including a specific frequency band resonance range (such as 6.78 MHz ± 0.3 MHz) and a short-distance coil layout (≤ 15 cm).

[0192] In the embodiments of the present application, based on the set of spatial density parameters, the genetic algorithm (NSGA-II) is used to optimize the multi-objective combination of the resonance frequency and the coil spacing. The objective function is defined as maximizing the output power (≥ 150 kW) and minimizing the electromagnetic radiation leakage (≤ 30 dBμV / m). The constraint conditions include the coil temperature rise (≤ 40 °C) and the efficiency threshold (≥ 85%). A parameter fitness surface is constructed through finite element simulation, and the Pareto front optimal solution is selected as the final parameter combination. A dynamic impedance matching network (calibrated based on the Smith chart) is used to adjust the resonance circuit parameters in real time to ensure stable power output.

[0193] 803. Synchronously configure a wideband resonance frequency range and a large-spacing power transmission coil parameter combination for the low-priority charging port, so that the output power range of the low-priority charging port covers the power interval corresponding to the conventional charging demand;

[0194] In step 803, the wideband resonance frequency range and the large-spacing power transmission coil parameter combination are electromagnetic coupling parameters set to adapt to the conventional charging demand, including a wide frequency band resonance range (such as 13.56 MHz ± 2 MHz) and a long-distance coil layout (≥ 30 cm).

[0195] In the embodiments of the present application, for the spatial distribution characteristics of low-priority ports, the ant colony optimization algorithm (ACO) is used to search for a coil layout scheme that meets the requirements of maximizing the coverage area (≥80 ㎡) and minimizing the energy consumption (≤5 kW). The optimal coil spacing is determined through the analysis of electromagnetic field uniformity (based on the numerical solution of Poisson's equation), and the multi-band adaptive switching is achieved by combining a broadband frequency tuning module (using software-defined radio technology). The output power range of the low-priority ports covers the power range corresponding to the conventional charging requirements, and a power factor correction circuit (PFC) is introduced to compensate for the reactive power loss, ensuring an efficiency ≥75% in the wide frequency band.

[0196] 804. Collect the actual output power fluctuation data of the different-priority charging ports. If a deviation from the corresponding power range is detected, recalculate the combination of the resonant frequency range and the power transmission coil spacing parameters based on the current fluctuation data.

[0197] In step 804, the actual output power fluctuation data is a record of the deviation between the power output value during the real-time operation of the wireless charging port and its target range, which is used to trigger the re-optimization of the parameters.

[0198] In the embodiments of the present application, the port output data is collected by a high-precision power sensor, and the wavelet transform algorithm is used to decompose the fluctuation signal to identify the high-frequency noise and the low-frequency trend component. If the trend component continuously deviates from the target range for more than 3 sampling periods (15 minutes), trigger the re-calculation process of the combination of the resonant frequency range and the power transmission coil spacing parameters: predict the change trend of the demand density based on the Kalman filter algorithm, re-execute the optimization process of steps 802-803 in combination with the current spatial density parameters, and dynamically update the parameter combination using the rolling horizon control (RHC) strategy.

[0199] The following is a specific example:

[0200] On the west side of the underground parking lot of a subway-integrated property complex is a fast-charging hot zone for daytime office use (from 7:00 to 19:00), and on the east side is a conventional demand area for nighttime residence (from 20:00 to 6:00). In step 801, kernel density estimation shows that the peak fast demand density within the coverage area of west-side ports P1 - P3 reaches 2.1 persons per square meter, with a coverage radius of 12 meters; in step 802, NSGA-II configures a resonance frequency of 6.78 MHz and a coil spacing of 10 cm for P1 - P3, and the output power is increased to 160 kW, with the radiation leakage controlled within 28 dBμV / m; in step 803, ACO optimizes a broadband frequency of 13.56 MHz and a spacing of 35 cm for east-side ports P4 - P6, with a coverage area of 85 square meters, and the single-port power stabilized at 28 kW; in step 804, during the noon period, it is detected that the actual output of P2 fluctuates to 140 kW (the target is 160 kW, and it continuously deviates from the target range for more than 3 sampling periods). The Kalman filter predicts the downward trend of demand density, and after readjusting the parameters, it resumes to 155 kW.

[0201] Steps 801 - 804 achieve high-precision matching of wireless charging power output and dynamic demand through kernel density quantization, multi-objective parameter optimization, broadband adaptive configuration, and fluctuation-driven recalculation. In the scenario of urban mixed-functional areas, it significantly improves the fast-charging response speed and the utilization rate of conventional equipment, reduces electromagnetic interference and energy consumption waste, and forms an all-link adaptive ability from demand perception, parameter optimization to dynamic closed-loop tuning.

[0202] Figure 2 The following is a schematic structural diagram of an intelligent site selection and evaluation system for charging piles provided by an embodiment of the present application, as Figure 2 shown. The system includes:

[0203] An acquisition module 21, configured to acquire mobile terminal communication data of a target area, and generate a demand period division model based on the spatio-temporal variation law of the crowd flow density in the mobile terminal communication data. The demand period division model is used to distinguish the fast-charging demand corresponding to the daytime period from the conventional charging demand corresponding to the nighttime period;

[0204] An adjustment module 22, configured to adjust the position of edge computing devices deployed in the target area according to the demand distribution result output by the demand period division model, so that the service range of the edge computing devices moves in unison with the peak area of the crowd flow density and meets the preset data transmission performance requirements;

[0205] A control module 23, configured to control the multi-port wireless charging system to switch the charging power output mode based on the charging demand type identified in the position adjustment result. The charging power output mode corresponds to the periods of the fast-charging demand and the conventional charging demand;

[0206] A generation module 24, configured to combine the network layout data after the position adjustment of the edge computing device with the power output mode information of the multi-port wireless charging system, and generate a set of candidate charging pile layout positions that simultaneously meet the daytime charging service efficiency and the optimization index of the device usage rate at night;

[0207] A screening module 25, configured to verify the safety distance of the underground pipe network for each position in the set of candidate charging pile layout positions, and screen out a target charging pile layout plan that meets the preset construction safety standards and matches the demand distribution law of the demand period division model.

[0208] Figure 2 The described charging pile intelligent site selection and evaluation system can execute Figure 1 The described charging pile intelligent site selection and evaluation method in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated. For the charging pile intelligent site selection and evaluation system in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0209] In a possible design, Figure 2 The charging pile intelligent site selection and evaluation system in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32;

[0210] The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0211] The processing component 32 is used for the Figure 1 charging pile intelligent site selection and evaluation method in the above

[0212] embodiment. Among them, the processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0213] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0214] Of course, the computing device may also necessarily include other components, such as an input / output interface, a display component, a communication component, etc.

[0215] The input / output interface provides an interface between the processing component and the peripheral interface module, and the peripheral interface module may be an output device, an input device, etc.

[0216] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0217] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device can refer to a cloud server, and the above-mentioned processing component, storage component, etc. can be basic server resources leased or purchased from the cloud computing platform.

[0218] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application 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 recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent site selection and evaluation method for charging piles, characterized in that, Including: Obtain the mobile terminal communication data of the target area, and generate a demand period division model based on the spatio-temporal variation law of the crowd density in the mobile terminal communication data. The demand period division model is used to distinguish the fast charging demand corresponding to the daytime period from the regular charging demand corresponding to the nighttime period; According to the demand distribution result output by the demand period division model, adjust the position of the edge computing device deployed in the target area so that the service range of the edge computing device moves in unison with the peak area of the crowd density; Based on the charging demand type identified in the position adjustment result, control the multi-port wireless charging system to switch the charging power output mode, and the charging power output mode corresponds to the periods of the fast charging demand and the regular charging demand; Combine the network layout data after the position adjustment of the edge computing device with the information corresponding to the power output mode of the multi-port wireless charging system to generate a set of candidate charging pile layout positions; Perform distance verification on each position in the set of candidate charging pile layout positions, and screen out the target charging pile layout scheme that meets the preset safety standard and matches the demand distribution law of the demand period division model; The adjusting the position of the edge computing device deployed in the target area according to the demand distribution result output by the demand period division model includes: Analyze the demand distribution result output by the demand period division model, extract the coordinate set of the high-demand area in the target area within the current period, and determine the movement trajectory of the peak area of the crowd density according to the spatio-temporal distribution characteristics of the coordinate set of the high-demand area; Based on the central positions of the peak areas in each time segment of the movement trajectory, calculate the set of target deployment positions of the edge computing device. The straight-line distance between each target position in the set of target deployment positions and the center of the peak area corresponding to the corresponding time segment does not exceed the preset coverage radius; Generate a device migration instruction according to the set of target deployment positions, drive the edge computing device to migrate to the target position according to the device migration instruction, and establish a communication network with adjacent devices during the migration process, and control the end-to-end transmission delay between nodes in the communication network to be lower than the preset maximum value; Obtain the updated coordinate set of the peak area through the communication network. When it is detected that the coverage overlap rate between the updated coordinate set and the set of target deployment positions is lower than the preset tolerance threshold, re-execute the calculation of the set of target deployment positions based on the updated coordinate set and synchronously adjust the device migration instruction.

2. The method according to claim 1, characterized in that, The combining the network layout data after the position adjustment of the edge computing device with the power output mode information of the multi-port wireless charging system to generate a set of candidate charging pile layout positions includes: Extract the network layout data after the position adjustment of the edge computing device and identify the continuous spatial area that meets the daytime charging service efficiency requirements; Synchronously obtain the power output mode information of the multi-port wireless charging system and mark the output area where the power utilization rate continuously exceeds the average level during the nighttime period; Perform a geospatial overlay of the continuous spatial region and the output region, and screen out candidate layout ranges that simultaneously contain the boundaries of the daytime efficiency region and the core area of nighttime utilization rate; Based on the candidate layout ranges, perform a spatial priority ranking on the deployable regions according to the preset charging pile spacing rules to generate a set of candidate charging pile layout positions.

3. The method according to claim 1, wherein Performing distance verification on each position in the set of candidate charging pile layout positions, and screening out a target charging pile layout plan that meets the preset safety standards and matches the demand distribution law of the demand period division model, including: Obtain the spatial distances between each position in the set of candidate charging pile layout positions and the three-dimensional coordinate data of the underground pipe network, and screen out a subset in which the straight-line distances from each position to the gas pipeline and the power pipe corridor are both greater than the preset safety distance; Based on the spatial distributions of the fast charging demand hotspots and the conventional charging demand hotspots marked in the demand period division model, calculate the area ratios of the subset covering the two types of demand hotspots, and retain the suitable positions where the area ratios simultaneously meet the lower limits of daytime fast demand and nighttime conventional demand coverage; Perform underground pipe network safety spacing verification on the suitable positions, eliminate abnormal positions where the spacing from adjacent pipe network positions exceeds the preset spacing interval, and generate a set of intermediate layout plans; Conduct a safety assessment based on the historical period pedestrian flow density curves in the set of intermediate layout plans, perform a similarity match between the inspection results and the demand distribution law of the demand period division model, and screen out a target charging pile layout plan that meets the preset safety standards and matches the demand distribution law.

4. The method according to claim 1, wherein Based on the charging demand types identified in the position adjustment results, controlling the multi-port wireless charging system to switch the charging power output mode, including: Obtain the charging demand types marked in the position adjustment results, and the charging demand types include the first type of demand signal and the second type of demand signal corresponding to the fast charging demand and the conventional charging demand respectively; According to the spatial distribution density of the charging demand types, configure a priority matching rule for each charging port of the multi-port wireless charging system, and the priority of the charging ports in the area covered by the first type of demand signal is higher than that of the second type of demand signal; Based on the priority matching rule, adjust the electromagnetic coupling parameter combinations of the charging ports in the multi-port wireless charging system so that the output power range of the high-priority charging ports adapts to the fast charging demand, and the output power range of the low-priority charging ports adapts to the conventional charging demand. The electromagnetic coupling parameter combinations include the resonant frequency matching range and the power transmission coil spacing; Through the electromagnetic coupling state feedback data of the multi-port wireless charging system, periodically detect the adaptation degree of the actual output power of each charging port to the priority matching rule. If it is detected that the adaptation degree is lower than the requirement of the matching rule, regenerate the electromagnetic coupling parameter combination and update the priority matching rule.

5. The method according to claim 1, characterized in that Generating a demand period division model based on the spatio-temporal variation law of the pedestrian flow density in the mobile terminal communication data, including: Extract the terminal device spatial coordinates and timestamps from the communication data of the mobile terminal, and construct a spatio-temporal distribution sequence of pedestrian flow density with geographical grids as units; Perform pattern recognition on the pedestrian flow density fluctuation characteristics within each geographical grid in the spatio-temporal distribution sequence of pedestrian flow density, and extract the grid set with short-term high-density aggregation characteristics during the daytime period as the fast charging demand candidate area, and the grid set with continuous medium and low density distribution during the nighttime period as the conventional charging demand candidate area; Based on the spatio-temporal overlap analysis of the fast charging demand candidate area and the conventional charging demand candidate area, merge the candidate areas with spatial coverage areas exceeding the overlap upper limit within adjacent time segments into demand period division units, and label each division unit with the corresponding charging demand type label; According to the label distribution law of the demand period division units within the historical period, correct the division granularity of the geographical grids and the determination threshold of the spatio-temporal overlap analysis, and generate a demand period division model adapted to the pedestrian flow change characteristics within the target area.

6. The method according to claim 1, wherein The generating device migration instructions according to the target deployment location set, driving the edge computing device to migrate to the target location according to the device migration instructions, and establishing a communication network with adjacent devices during the migration process, and controlling the end-to-end transmission delay between each node in the communication network to be lower than a preset maximum value, includes: Generate device migration instructions including migration paths and migration speeds according to the relative distances between each target location in the target deployment location set and the location of the current edge computing device; Drive the edge computing device to migrate to the target location according to the device migration instructions, detect the signal strength with adjacent edge computing devices during the migration process, and select the adjacent devices with signal strength higher than the preset threshold as candidate nodes for the communication network; Based on the location distribution and signal strength data of the candidate nodes, construct a star-shaped communication network topology centered on the edge computing device; Monitor the end-to-end transmission delay between each topology node in the star-shaped communication network topology. If it is detected that the end-to-end transmission delay exceeds the preset maximum value, re-select the candidate nodes and adjust the hop count distribution of the star-shaped communication network topology.

7. The method according to claim 4, wherein The adjusting the electromagnetic coupling parameter combinations of each charging port in the multi-port wireless charging system, so that the output power range of the high-priority charging port adapts to the fast charging demand, and the output power range of the low-priority charging port adapts to the conventional charging demand, includes: According to the spatial distribution of different priority charging ports marked in the priority matching rule, extract the spatial density parameters of the fast charging demand within the coverage area of the high-priority charging port; Based on the spatial density parameters, configure a narrowband resonance frequency range and a small-spacing power transmission coil parameter combination for each high-priority charging port, so that the output power range of the high-priority charging port covers the power interval corresponding to the fast charging demand; Synchronously configure a broadband resonance frequency range and a large-spacing power transmission coil parameter combination for the low-priority charging port, so that the output power range of the low-priority charging port covers the power interval corresponding to the conventional charging demand; Collect the actual output power fluctuation data of the different-priority charging ports. If a deviation from the corresponding power range is detected, recalculate the resonant frequency range and the power transfer coil spacing parameter combination based on the current fluctuation data.

8. An intelligent site selection evaluation system for charging piles, characterized in that, Including: An acquisition module, configured to acquire mobile terminal communication data of a target area, generate a demand period division model based on the spatio-temporal variation law of the crowd density in the mobile terminal communication data, and the demand period division model is used to distinguish the fast charging demand corresponding to the daytime period from the regular charging demand corresponding to the nighttime period; An adjustment module, configured to adjust the position of the edge computing device deployed in the target area according to the demand distribution result output by the demand period division model, so that the service range of the edge computing device moves in unison with the peak area of the crowd density and meets the preset data transmission performance requirements; A control module, configured to control the multi-port wireless charging system to switch the charging power output mode based on the charging demand type identified in the position adjustment result, and the charging power output mode corresponds to the periods of the fast charging demand and the regular charging demand; A generation module, configured to combine the network layout data after the position adjustment of the edge computing device with the power output mode information of the multi-port wireless charging system to generate a candidate charging pile layout position set that simultaneously meets the daytime charging service efficiency and the nighttime device utilization rate optimization indicators; A screening module, configured to verify the safety distance of the underground pipe network for each position in the candidate charging pile layout position set, and screen out a target charging pile layout scheme that meets the preset construction safety standards and matches the demand distribution law of the demand period division model; Adjusting the position of the edge computing device deployed in the target area according to the demand distribution result output by the demand period division model includes: Analyze the demand distribution result output by the demand period division model, extract the high-demand area coordinate set in the target area during the current period, and determine the movement trajectory of the peak area of the crowd density according to the spatio-temporal distribution characteristics of the high-demand area coordinate set; Based on the center positions of the peak areas of each time segment in the movement trajectory, calculate the target deployment position set of the edge computing device, and the straight-line distance between each target position in the target deployment position set and the center of the peak area of the corresponding time segment does not exceed the preset coverage radius; Generate a device migration instruction according to the target deployment position set, drive the edge computing device to migrate to the target position according to the device migration instruction, and establish a communication network with adjacent devices during the migration process, and control the end-to-end transmission delay between each node in the communication network to be lower than the preset maximum value; Obtain the updated coordinate set of the peak area through the communication network. When it is detected that the coverage overlap rate between the updated coordinate set and the target deployment position set is lower than the preset tolerance threshold, recalculate the target deployment position set based on the updated coordinate set and synchronously adjust the device migration instruction.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for intelligent site selection and evaluation of a charging pile as described in any one of claims 1 to 7.

Images