A traffic energy load demand analysis method and system

Abstract

This application provides a method and system for analyzing traffic energy load demand, applied in the field of energy load analysis. It dynamically acquires multi-dimensional data within a predicted area, including the usage status of energy replenishment stations, pedestrian density index, commercial activity intensity, and the battery status of high-power vehicles. Based on this data, it comprehensively determines whether a high-power energy replenishment cluster has formed. Once a high-power energy replenishment cluster is identified, it further acquires predicted and real-time power loads, and simulates and overlays them to calculate the instantaneous impact. By determining whether the instantaneous impact exceeds a preset risk threshold, it promptly issues risk warnings and provides scheduling suggestions. This application significantly improves the accuracy and real-time performance of urban traffic energy load analysis, providing strong technical support for refined scheduling of energy distribution networks, dynamic optimization of energy replenishment infrastructure, and early warning of potential risks, effectively ensuring the stability and reliability of urban energy supply.

Description

Technical Field

[0001] This application relates to the field of energy load analysis, and more specifically, to a method and system for analyzing transportation energy load demand. Background Technology

[0002] In urban traffic energy load analysis, traditional methods primarily predict regional or temporal energy demand by aggregating overall vehicle energy consumption data, such as the average energy consumption and refueling habits of electric vehicles. This approach has historically been instructive for the long-term development of energy distribution networks and the site selection of refueling stations. However, with the rapid advancement of electric vehicle technology, particularly the significant increase in battery energy storage capacity and the acceleration of refueling speed, users' energy refueling behavior patterns have changed significantly. For example, users tend to refuel only when the battery is low and more frequently utilize fragmented time for short, high-power rapid refueling.

[0003] These changes make it difficult for traditional analysis methods to accurately capture localized, transient, and high-intensity energy replenishment peaks. For example, in non-traditional energy replenishment hotspots and during off-peak hours, a large number of high-capacity electric vehicles may suddenly replenish energy simultaneously at high power, forming "opportunistic" high-power energy replenishment clusters. The emergence of such clusters puts unprecedented pressure on local energy distribution networks, potentially leading to transformer overload, sudden voltage drops in lines, and even regional power outages. Traditional load analysis methods, based on historical average data and typical commuting patterns, cannot anticipate such localized, transient, and high-intensity energy replenishment demand concentrations, thus masking the real risks and potential service bottlenecks faced by energy distribution networks. Therefore, existing technologies urgently need improvement to establish an analytical mechanism capable of dynamically sensing and predicting the impact of electric vehicle technology evolution and changes in user behavior on traffic energy load. This would provide forward-looking data support for refined scheduling of energy distribution networks, dynamic optimization of energy replenishment infrastructure, and early warning of potential risks.

[0004] Therefore, providing a method and system for analyzing traffic energy load demand is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This application discloses a method and system for analyzing traffic energy load demand, which aims to solve the problem that traditional traffic energy load analysis methods are unable to accurately capture local, instantaneous, and high-intensity energy replenishment peaks, thereby masking the real risks and potential service bottlenecks faced by the energy distribution network.

[0006] The technical solution of this application is as follows:

[0007] In a first aspect, this application discloses a method for analyzing traffic energy load demand, applied in the field of energy load analysis, comprising the following steps:

[0008] Within the predicted area, the usage status of energy replenishment stations is obtained according to the preset data transmission protocol, and the pedestrian density index, commercial activity intensity, and high-power vehicle battery status are obtained respectively.

[0009] When the usage status of energy replenishment stations, the population density index, the commercial activity intensity, and the battery status of high-power vehicles in the predicted area all meet the preset conditions, it is defined that a high-power energy replenishment cluster will be formed in the predicted area within a preset time period.

[0010] Obtain the predicted power load in the high-power energy replenishment cluster and the real-time power load in the prediction area, simulate and superimpose the predicted power load and the real-time power load, and calculate and obtain the instantaneous impact;

[0011] Determine whether the instantaneous impact exceeds the preset risk threshold. If so, issue a risk warning and provide scheduling suggestions.

[0012] This technical solution enables dynamic perception and prediction of the impact of electric vehicle technology evolution and changes in user behavior on traffic energy load, thereby providing forward-looking data support for the refined scheduling of energy distribution networks, the dynamic optimization of energy replenishment infrastructure, and early warning of potential risks. It effectively solves the problem that traditional methods cannot accurately capture local, instantaneous, and high-intensity energy replenishment peaks.

[0013] Furthermore, the pedestrian density index is obtained in the following way:

[0014] Obtain the number of active users and wireless network connected devices within the predicted area;

[0015] The population density index within the predicted area is obtained by combining the sum of the number of active users and the number of wireless network connected devices with the predicted area area.

[0016] This technical solution enables more accurate quantification and prediction of population density within a region, providing a specific and operable method for obtaining the population density index, thereby improving the accuracy of identifying high-power energy replenishment clusters.

[0017] In some preferred implementations, the popularity of business activities is obtained in the following ways:

[0018] Obtain real-time check-in volume related to the predicted region on social media platforms;

[0019] Obtain real-time data on changes in the number and value of transactions within the prediction area;

[0020] The data on real-time check-in volume, real-time transaction volume, and transaction amount changes are weighted and summed to calculate the popularity of business activities.

[0021] This technical solution can integrate multi-dimensional data to more comprehensively and in real time reflect the commercial activity level of the predicted area, providing a more accurate indicator of commercial activity heat for the identification of high-power energy replenishment clusters.

[0022] Furthermore, when the usage status of energy replenishment stations, pedestrian density index, commercial activity intensity, and high-power vehicle battery status within the predicted area all meet preset conditions, the predicted area is defined as forming a high-power energy replenishment cluster within a preset time period, including the following steps:

[0023] Based on the usage status of the energy replenishment stations within the predicted area, determine whether the predicted area is a traditional energy replenishment hotspot area, and record it as the first judgment result;

[0024] If the first judgment result is negative, determine whether the pedestrian density index of the predicted area exceeds the pedestrian density index threshold within a preset time period, and record it as the second judgment result.

[0025] Determine whether there are more than a preset number of electric vehicles with low battery levels in the vicinity of the prediction area, and record this as the third judgment result.

[0026] If the commercial activity intensity within the predicted area exceeds a preset intensity threshold, it is recorded as the fourth judgment result.

[0027] When the second, third, and fourth judgment results are all yes, the prediction area is defined to form a high-power energy replenishment cluster within a preset time period.

[0028] This technical solution enables the accurate identification of potential high-power energy replenishment clusters in non-traditional hotspot areas through multiple judgment mechanisms, effectively avoiding the omission of "opportunistic" clusters by traditional methods and improving the timeliness and accuracy of early warning.

[0029] Based on this, the predicted power load is obtained in the following way:

[0030] Obtain the number of electric vehicles with low battery status in the vicinity of the prediction area, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment.

[0031] Based on the number of electric vehicles with low battery status in the surrounding area, the pedestrian density index, and the intensity of commercial activities, the number of vehicles that can simultaneously replenish high-power energy is obtained.

[0032] The predicted power load is obtained based on the number of vehicles simultaneously receiving high-power energy replenishment, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment.

[0033] This technical solution can comprehensively consider the number of vehicles, individual charging capabilities, and user preferences to more accurately predict the power load that high-power energy replenishment clusters may generate, providing a more reliable data foundation for subsequent instantaneous impact assessments.

[0034] As a technological improvement, the predicted power load in the high-power energy replenishment cluster and the real-time power load within the predicted area are obtained. The predicted power load and the real-time power load are then simulated and superimposed to calculate the instantaneous impact, including the following steps:

[0035] Obtain real-time operational data and design capacity data of the end-point energy distribution network within the predicted area;

[0036] The predicted power load is superimposed onto the end-point energy distribution network within the prediction area to obtain the sum of the predicted power load and the real-time power load;

[0037] The voltage drop percentage is obtained based on the predicted power load, line impedance, and rated voltage.

[0038] The predicted maximum temperature rise is obtained by summing the predicted power load and the real-time power load, and the real-time ambient temperature.

[0039] The predicted line current is obtained by summing the predicted power load and the real-time power load, and by the real-time line voltage.

[0040] The voltage drop percentage, the predicted maximum temperature rise, and the predicted line current are considered as instantaneous effects.

[0041] The real-time operating data includes: real-time power load, real-time ambient temperature, and real-time line voltage;

[0042] Design load data includes: rated voltage and line impedance.

[0043] This technical solution enables the simulation and overlay to predict loads and calculate key indicators such as voltage drop, temperature rise, and line current, thus comprehensively assessing the instantaneous impact of high-power energy replenishment clusters on local energy distribution networks and providing a quantitative basis for risk warning.

[0044] To refine the plan, determine whether the instantaneous impact exceeds the preset risk threshold. If so, issue a risk warning and provide scheduling suggestions, including the following steps:

[0045] Determine whether the voltage drop percentage exceeds the preset voltage stability risk threshold and record it as the fifth judgment result;

[0046] Determine whether the predicted maximum temperature rise exceeds the preset temperature risk threshold and record it as the sixth judgment result.

[0047] Determine whether the predicted line current exceeds the rated current, and record this as the seventh judgment result;

[0048] Based on the fifth, sixth, and seventh judgment results, a risk warning is issued and corresponding scheduling suggestions are provided.

[0049] The design load data also includes: rated current.

[0050] This technical solution enables a more comprehensive and accurate identification of potential risks faced by energy distribution networks based on multi-dimensional risk assessment, and provides targeted scheduling suggestions, thereby improving the practicality and effectiveness of risk warning.

[0051] To enhance functionality, the following steps are included after obtaining the predicted power load:

[0052] Obtain the actual movement trajectory of each high-power electric vehicle with a low battery status around the prediction area, and construct the expected movement path for each electric vehicle based on the initial intent.

[0053] The system compares the actual movement trajectory and expected movement path of each electric vehicle in real time, detects and identifies the behavioral deviations of each electric vehicle caused by environmental discomfort, and classifies them into different behavioral deviation types.

[0054] Obtain the intensity and duration of current environmental discomfort, and generate behavioral response correction factors based on the type of behavioral deviation;

[0055] The number of vehicles simultaneously receiving high-power energy replenishment and the predicted power load are adjusted based on the behavioral response correction factor. The risk warning information is then updated based on the adjusted number of vehicles simultaneously receiving high-power energy replenishment and the adjusted predicted power load.

[0056] This technical solution enables real-time monitoring of electric vehicle behavior deviations and corrections based on environmental factors, dynamically adjusting predicted power load to make risk warning information more closely reflect actual conditions and improve the flexibility and accuracy of predictions.

[0057] As a further improvement, after obtaining the predicted power load, the following steps are also included:

[0058] When each high-power electric vehicle with a low battery status in the vicinity of the prediction area connects to the energy replenishment station in the prediction area, the real-time communication data of the battery management system of each electric vehicle is obtained.

[0059] Analyze real-time communication data from the battery management system to obtain the actual battery temperature and actual maximum energy replenishment power for each electric vehicle;

[0060] The local ambient temperature of the energy replenishment station within the prediction area is obtained, and the local ambient temperature is correlated with the actual battery temperature of each electric vehicle to generate the cause of the energy replenishment power limitation.

[0061] Based on the reasons for the energy replenishment power limitation and the actual maximum energy replenishment power of each electric vehicle, the predicted power load is corrected, and the risk warning information is updated based on the corrected predicted power load.

[0062] This technical solution allows for more precise correction of predicted power load by acquiring the actual state of the electric vehicle battery and the ambient temperature. It takes into account the limitations of the battery itself and the environment on the charging power, further improving the accuracy and reliability of the prediction.

[0063] Secondly, this application also discloses a traffic energy load demand analysis system, applied in the field of energy load analysis, including:

[0064] The prediction area parameter acquisition module is used to obtain the usage status of energy replenishment stations within the prediction area according to a preset data transmission protocol, and to obtain the pedestrian density index, commercial activity heat and high-power vehicle power status respectively.

[0065] The high-power energy replenishment cluster formation module is used to define that a high-power energy replenishment cluster will be formed in the predicted area within a preset time period when the usage status of energy replenishment stations, the population density index, the commercial activity intensity, and the power status of high-power vehicles in the predicted area all meet preset conditions.

[0066] The instantaneous impact acquisition module is used to acquire the predicted power load in the high-power energy replenishment cluster and the real-time power load in the prediction area, simulate and superimpose the predicted power load and the real-time power load, and calculate and acquire the instantaneous impact.

[0067] The risk warning and scheduling module is used to determine whether the instantaneous impact exceeds the preset risk threshold. If so, it issues a risk warning and provides scheduling suggestions.

[0068] This technical solution provides a system for implementing the aforementioned traffic energy load demand analysis method. Through modular design, it enables dynamic perception, prediction, assessment, and early warning of traffic energy load, providing hardware and software support for the intelligent management of energy distribution networks.

[0069] Beneficial effects

[0070] The traffic energy load demand analysis method disclosed in this application dynamically acquires multi-dimensional data such as the usage status of energy replenishment stations, pedestrian density index, commercial activity intensity, and high-power vehicle battery status within the prediction area, and comprehensively judges whether a high-power energy replenishment cluster has formed based on this data. Once a high-power energy replenishment cluster is identified, the method further acquires the predicted power load and real-time power load, and simulates and superimposes them to calculate the instantaneous impact, including key indicators such as voltage drop percentage, predicted maximum temperature rise, and predicted line current. Finally, by judging whether the instantaneous impact exceeds a preset risk threshold, a risk warning is issued in a timely manner and scheduling suggestions are provided.

[0071] This method effectively solves the problem that traditional load analysis methods in the prior art cannot accurately capture localized, instantaneous, and high-intensity energy replenishment peaks. By introducing real-time dynamic data such as pedestrian density index, commercial activity intensity, and the battery status of high-power vehicles, this application can more accurately identify "opportunistic" high-power energy replenishment clusters, making up for the shortcomings of traditional methods that rely solely on average data and typical commuting patterns. Furthermore, through quantitative assessment of instantaneous impacts, it can intuitively reflect the real risks faced by the energy distribution network, avoiding potential service bottlenecks. Therefore, this application can provide forward-looking data support for the refined scheduling of energy distribution networks, the dynamic optimization of energy replenishment infrastructure, and the early warning of potential risks, significantly improving the accuracy and real-time performance of urban traffic energy load analysis, and has significant practical application value. Attached Figure Description

[0072] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0073] Figure 1 A flowchart illustrating a traffic energy load demand analysis method provided in this application embodiment;

[0074] Figure 2 A flowchart for obtaining the popularity of commercial activities in step S1 provided in the embodiments of this application;

[0075] Figure 3 A flowchart of step S2 provided in an embodiment of this application;

[0076] Figure 4 A flowchart for obtaining the predicted power load in step S3 provided in the embodiments of this application;

[0077] Figure 5A flowchart of step S3 provided in the embodiments of this application;

[0078] Figure 6 A flowchart of the first implementation method after step C3 provided in this application embodiment;

[0079] Figure 7 A flowchart of the second implementation method after step C3 provided in this application embodiment.

[0080] Figure 8 This is a schematic diagram of the structure of a traffic energy load demand analysis system provided in an embodiment of this application. Detailed Implementation

[0081] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0082] The embodiments in this application are written in a progressive manner.

[0083] Traditional urban traffic energy load analysis methods primarily predict regional or temporal energy demand by aggregating overall vehicle energy consumption data, such as the average energy consumption and refueling habits of electric vehicles. This approach has historically been instructive for the long-term development of energy distribution networks and the site selection of refueling stations. However, with the rapid advancement of electric vehicle technology, particularly the significant increase in battery energy storage capacity and the acceleration of refueling speed, users' refueling behavior patterns have changed significantly. For example, users tend to refuel only when their batteries are low and more frequently utilize fragmented time for short-duration, high-power rapid refueling. These changes make it difficult for traditional analysis methods to accurately capture localized, instantaneous, and high-intensity energy refueling peaks. For instance, in non-traditional refueling hotspots and during off-peak hours, a large number of high-capacity electric vehicles may suddenly engage in high-power refueling simultaneously, forming "opportunistic" high-power refueling clusters. The emergence of such clusters puts unprecedented pressure on local energy distribution networks, potentially leading to transformer overload, sudden voltage drops in lines, and even regional power outages. Traditional load analysis methods, based on historical average data and typical commuting patterns, cannot anticipate such localized, instantaneous, and high-intensity concentrations of energy replenishment demand, thus masking the real risks and potential service bottlenecks faced by energy distribution networks.

[0084] like Figure 1As shown, this application proposes a traffic energy load demand analysis method, applied to the field of energy load analysis, including the following steps:

[0085] S1. Within the predicted area, obtain the usage status of the energy replenishment station according to the preset data transmission protocol, and obtain the pedestrian density index, commercial activity intensity and high-power vehicle power status respectively.

[0086] S2. When the usage status of energy replenishment stations, the population density index, the commercial activity intensity, and the power status of high-power vehicles in the prediction area all meet the preset conditions, it is defined that a high-power energy replenishment cluster will be formed in the prediction area within a preset time period.

[0087] S3. Obtain the predicted power load in the high-power energy replenishment cluster and the real-time power load in the prediction area, simulate and superimpose the predicted power load and the real-time power load, and calculate and obtain the instantaneous impact;

[0088] S4. Determine whether the instantaneous impact exceeds the preset risk threshold. If so, issue a risk warning and provide scheduling suggestions.

[0089] The prediction area in step S1 refers to a geographically defined specific area, such as a city block, a business center, or a transportation hub, and is the smallest unit for energy load analysis. Energy replenishment stations refer to facilities that provide energy replenishment services for electric vehicles, including but not limited to charging stations and battery swapping stations. The preset data transmission protocol can be any standard or non-standard communication protocol, such as MQTT, HTTP, Modbus, etc., to ensure accurate and efficient data transmission between different devices and systems. The pedestrian density index is an indicator that measures the density of people within the prediction area, reflecting potential energy replenishment needs. The commercial activity heat index reflects the level of commercial activity within the prediction area and is usually closely related to pedestrian density and vehicle activity. The high-power vehicle battery status refers to the current battery level of electric vehicles, especially those vehicles that support rapid energy replenishment.

[0090] When these indicators meet the preset conditions in step S2, it indicates that a high-power energy replenishment cluster may be formed in the predicted area within a specific time period, that is, a phenomenon in which a large number of electric vehicles simultaneously replenish high-power energy.

[0091] The predicted power load in step S3 can be obtained based on a comprehensive analysis of the number of electric vehicles in the high-power energy replenishment cluster, the theoretical maximum energy replenishment power of each electric vehicle, and the high-power energy replenishment preference intensity factor. The real-time power load can be directly obtained from the real-time operating data of the end-point energy distribution network within the prediction area. By simulating and superimposing the predicted power load and the real-time power load, a comprehensive instantaneous total load can be obtained.

[0092] The preset risk thresholds in step S4 may include voltage stability risk thresholds, temperature risk thresholds, and rated current thresholds. For example, when the voltage drop percentage exceeds the preset voltage stability risk threshold, or the predicted maximum temperature rise exceeds the preset temperature risk threshold, or the predicted line current exceeds the rated current, the system will determine that a risk exists and immediately issue a risk warning. Simultaneously, the system will provide corresponding dispatching suggestions based on the specific risk type and severity. For example, it may suggest that energy replenishment stations limit the power output of some energy replenishment piles, or suggest that the power grid dispatch center adjust the energy allocation strategy within the region to avoid potential overload or power outage risks.

[0093] This application's method for analyzing traffic energy load demand introduces multi-dimensional data sources, including the usage status of energy replenishment stations, pedestrian density index, commercial activity intensity, and the battery status of high-power vehicles, to construct a more comprehensive and refined load forecasting model. Compared to traditional methods that rely solely on aggregated vehicle energy consumption data, this application can dynamically sense and predict localized, instantaneous, and high-intensity energy replenishment peaks, i.e., the formation of "high-power energy replenishment clusters." This forward-looking predictive capability enables the energy distribution network to identify potential overload risks in advance and issue timely risk warnings, providing specific scheduling recommendations. For example, under traditional methods, a non-traditional energy replenishment hotspot area may experience local grid overload due to a sudden surge in energy replenishment by a large number of high-power electric vehicles, but traditional methods cannot provide early warnings. However, this application, by monitoring pedestrian flow, commercial activity, and vehicle battery status in real time, can identify the formation of such "opportunistic" clusters in advance and calculate their instantaneous impact on the grid, thereby avoiding potential risks. Therefore, this application significantly improves the accuracy and real-time performance of urban traffic energy load analysis, providing strong technical support for the refined scheduling of energy distribution networks, the dynamic optimization of energy replenishment infrastructure, and the early warning of potential risks, effectively ensuring the stability and reliability of urban energy supply.

[0094] Specifically, in the above-mentioned method for analyzing traffic energy load demand, the pedestrian density index is obtained in the following way:

[0095] Obtain the number of active users and wireless network connected devices within the predicted area;

[0096] The population density index within the predicted area is obtained by combining the sum of the number of active users and the number of wireless network connected devices with the predicted area area.

[0097] The number of active users can be understood as the number of users with active behavior within a specific time period in the predicted area. This can be calculated, for example, through user registration information from mobile communication networks, application usage data, or geolocation service data. The number of connected wireless devices refers to the number of devices connected to wireless networks within the predicted area. This can be obtained, for example, by counting the number of connected devices at Wi-Fi hotspots or cellular base stations. The predicted area area refers to the actual area of ​​the geographical region where population density analysis is conducted. Obtaining this data provides a more comprehensive reflection of the population density within the predicted area.

[0098] The above steps are the specific implementation details of obtaining the pedestrian density index in step S1. By comprehensively considering the number of active users and the number of wireless network connected devices within the predicted area, the intensity of human activity in that area can be more accurately reflected. The number of active users directly reflects the level of human participation, while the number of wireless network connected devices provides auxiliary information on pedestrian density from the device level. Correlating the sum of the two with the area of ​​the predicted area can effectively quantify the pedestrian density within the area, providing reliable data support for the subsequent judgment of the formation of high-power energy replenishment clusters. Thus, the acquisition of the pedestrian density index is no longer limited to a single dimension, but improves its accuracy and representativeness through multi-source data fusion.

[0099] Through the above technical solution, the method for obtaining the pedestrian density index has been defined specifically and quantitatively. This method, based on the number of active users and wireless network connected devices, can more accurately capture the population gathering and movement within the prediction area, avoiding the estimation bias that may exist in traditional methods. Therefore, it provides a more reliable data foundation for calculating the pedestrian density index, thereby improving the accuracy of judging the formation of high-power energy replenishment clusters, and enhancing the overall accuracy of traffic energy load demand analysis. This contributes to more effective risk warning and scheduling recommendations.

[0100] like Figure 2 As shown, the popularity of commercial activities is obtained in the following ways:

[0101] A1. Obtain the real-time check-in volume related to the predicted area on social media platforms;

[0102] A2. Obtain real-time data on changes in the number and value of transactions within the prediction area;

[0103] A3. Weight the real-time check-in volume, real-time transaction volume, and transaction amount change data respectively, and sum them to calculate the popularity of business activities.

[0104] The real-time check-in volume related to the predicted area on social platforms in step A1 refers to the analysis of publicly available user data on various social media platforms, such as location check-ins and event announcements, to statistically analyze the frequency and number of user activities in a specific predicted area in real time. This real-time check-in volume can intuitively reflect the degree of population gathering and activity in the area.

[0105] Step A2, obtaining real-time transaction volume and transaction value data within the forecast area, refers to collecting and analyzing the dynamic changes in the total number of goods or services transactions and transaction value occurring within the forecast area in real time through channels such as commercial transaction systems and payment platforms. This data directly reflects the economic activity and consumption capacity of the region.

[0106] Step A3 involves assigning weights to and summing the real-time check-in volume, real-time transaction volume, and transaction value changes to calculate the business activity heat index. This means that when comprehensively assessing business activity heat index, different importance coefficients (i.e., weights) can be assigned to different data sources based on their impact on energy load demand. For example, transaction value changes may more directly reflect the potential demand for high-power equipment than simple check-in volume, and therefore can be given a higher weight. By summing these weighted data, a comprehensive business activity heat index can be obtained, which can more comprehensively and accurately reflect the level of business activity in the predicted area.

[0107] Steps A1 to A3 detail the specific implementation of obtaining the commercial activity heat index in step S1. Through multi-dimensional data collection and weighted fusion mechanisms, a more refined commercial activity heat index assessment model is constructed. Traditional commercial activity assessments may rely on a single indicator, making them susceptible to data bias or bias. However, this application integrates real-time check-in data from social media platforms, real-time transaction volume within the region, and transaction value changes, assigning different weights based on their actual correlation with energy load. This allows the calculated commercial activity heat index to more comprehensively and accurately reflect the true level of commercial activity within the region. This precise commercial activity heat index, as a key condition for judging the formation of high-power energy replenishment clusters, effectively improves the accuracy of identifying potential energy load peaks, thus providing a more reliable input for subsequent instantaneous impact calculations and risk warnings.

[0108] Through the aforementioned technical solution, the acquisition of commercial activity heat no longer relies on a single or partial data source. Instead, it integrates real-time check-in data from social platforms, real-time transaction volume within the region, and transaction value changes, and performs weighted summation to construct a more comprehensive, refined, and dynamic commercial activity evaluation index. This multi-dimensional data fusion and weighted processing significantly improves the accuracy and representativeness of commercial activity heat assessment, making the judgment on the formation of high-power energy replenishment clusters within the predicted region more accurate. Therefore, this application can more effectively identify potential energy load peaks, providing a more solid data foundation for subsequent instantaneous impact calculations, risk warnings, and scheduling recommendations, thereby improving the reliability and practicality of the entire transportation energy load demand analysis method.

[0109] like Figure 3 As shown, specifically, the step of defining the formation of a high-power energy replenishment cluster in the predicted area within a preset time period when the usage status of energy replenishment stations, pedestrian density index, commercial activity intensity, and high-power vehicle battery status all meet preset conditions can further include the following judgment process:

[0110] B1. Based on the usage status of energy replenishment stations within the predicted area, determine whether the predicted area is a traditional energy replenishment hotspot area, and record it as the first judgment result;

[0111] B21. If the first judgment result is negative, determine whether the pedestrian density index of the predicted area exceeds the pedestrian density index threshold within a preset time period, and record it as the second judgment result.

[0112] B22. Determine whether there are more than the preset number of electric vehicles with low battery status in the surrounding area of ​​the prediction area, and record it as the third judgment result;

[0113] B23. If the commercial activity intensity within the predicted area exceeds the preset intensity threshold, record it as the fourth judgment result;

[0114] B3. When the second, third, and fourth judgment results are all yes, the prediction area is defined to form a high-power energy replenishment cluster within a preset time period.

[0115] The first judgment in step B1 aims to preliminarily screen areas that are known or historically shown to have consistently strong energy replenishment demand. For example, based on historical data analysis, areas with consistently high energy replenishment station utilization and significant peak-hour loads can be defined as traditional energy replenishment hotspots. If a predicted area is identified as a traditional energy replenishment hotspot, no further judgment is needed, and it can be directly determined that it will form a high-power energy replenishment cluster.

[0116] If the first judgment result in step B21 is negative, meaning the predicted area is not a traditional energy replenishment hotspot, a more detailed dynamic assessment is required. In this case, the second judgment result is used to assess whether the pedestrian density index of the predicted area exceeds a preset threshold within a preset time period. An increase in the pedestrian density index usually indicates increased human activity in the area, which may lead to increased traffic flow and electric vehicle usage frequency, thereby indirectly increasing energy replenishment demand.

[0117] The third judgment result in step B22 is used to detect whether there are more than a preset number of high-power electric vehicles with low battery levels in the vicinity of the predicted area. This judgment directly focuses on potential high-power energy replenishment needs, namely, electric vehicles with insufficient battery power that require high-power replenishment. The preset number can be set according to factors such as the size of the area and the capacity of the energy replenishment station;

[0118] The fourth judgment result in step B23 is used to assess whether the commercial activity intensity within the predicted area exceeds a preset intensity threshold. Commercial activity intensity can reflect the economic activity level and attractiveness of a region. High-intensity areas are often accompanied by more transportation and logistics activities, which may trigger concentrated energy replenishment demand.

[0119] In step B3, when the second, third, and fourth judgment results are all yes—that is, in a non-traditional hotspot area, when the conditions of high pedestrian density, a large number of low-battery, high-power vehicles in the surrounding area, and high commercial activity are simultaneously met—this predicted area will be defined as a high-power energy replenishment cluster within a preset time period. This comprehensive judgment mechanism ensures the accurate identification of emerging or dynamically formed high-power energy replenishment clusters.

[0120] Steps B1 to B3 are the specific implementation details of step S2. They introduce a multi-layered judgment mechanism to more precisely define the formation conditions of high-power energy replenishment clusters. First, a primary judgment quickly identifies traditional energy replenishment hotspots, avoiding redundant analysis of known situations and improving efficiency. Second, for non-traditional hotspots, the solution comprehensively considers three key dynamic indicators: pedestrian density index, high-power vehicle battery status, and commercial activity intensity. The pedestrian density index reflects the potential activity intensity of a region at a macro level; the detection of high-power vehicle battery status directly captures the specific sources of energy replenishment demand; and the assessment of commercial activity intensity provides a supplementary judgment on regional vitality from an economic activity perspective. By comparing these dynamic indicators with preset thresholds and requiring them to be met simultaneously, areas that may form high-power energy replenishment demand in a short period due to the superposition of multiple factors can be effectively identified, thereby achieving early warning of potential load peaks.

[0121] Through the aforementioned technical solution, this application enables a more accurate and comprehensive identification of high-power energy replenishment clusters in transportation energy load demand. Compared to relying solely on single or vague preset conditions, this solution significantly enhances the ability to detect emerging or unconventional high-power energy replenishment clusters by introducing preliminary assessments of traditional hotspot areas and comprehensive evaluations of multi-dimensional dynamic indicators such as pedestrian density, the number of low-power, high-power vehicles, and the intensity of commercial activities. This helps energy management systems predict instantaneous high load demand in local areas earlier and more accurately, providing a solid data foundation for subsequent risk warnings and dispatch recommendations. This effectively avoids problems such as grid instability or overload of energy replenishment facilities caused by sudden load surges, thereby improving the operational reliability and efficiency of the energy system.

[0122] In some of the embodiments described above in this application, traditional existing methods for analyzing traffic energy load demand may rely solely on simple statistics or experience to estimate the predicted power load in high-power energy replenishment clusters, without fully considering the various dynamic factors affecting actual energy replenishment demand. If this problem is not addressed, this coarse prediction method may lead to significant deviations between the predicted power load and the actual situation, thereby affecting the accuracy of instantaneous impact calculations, reducing the reliability of risk warnings and dispatch recommendations, and potentially even causing grid overload or improper resource allocation.

[0123] In response, this application further proposes a specific method for obtaining predicted power load. By comprehensively considering the number of electric vehicles, their theoretical maximum energy replenishment power, the preference intensity factor for high-power energy replenishment, the pedestrian density index, and the heat of commercial activities, the power load in high-power energy replenishment clusters can be predicted more accurately.

[0124] like Figure 4 As shown, specifically, the predicted power load is obtained in the following way:

[0125] C1. Obtain the number of high-power electric vehicles with low battery status around the prediction area, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment.

[0126] C2. Based on the number of high-power vehicles with low battery status in the surrounding area, the pedestrian density index, and the intensity of commercial activities, obtain the number of vehicles that can simultaneously replenish high-power energy.

[0127] C3. Based on the number of vehicles simultaneously receiving high-power energy replenishment, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment, obtain the predicted power load.

[0128] In step C1, "high-power vehicles with low battery status" refers to electric vehicles whose battery level is below a preset threshold, such as vehicles with less than 20% or 30% battery level. These vehicles typically have a strong need for energy replenishment. The number of high-power vehicles with low battery status can be obtained in real time through vehicle identification systems, IoT devices, or data interaction with the vehicle management platform. The theoretical maximum energy replenishment power of each electric vehicle refers to the maximum charging power that the electric vehicle model can accept under ideal conditions. This data is usually provided by the vehicle manufacturer and can be stored in a database. The high-power energy replenishment preference intensity factor is a coefficient between 0 and 1, used to quantify the likelihood and willingness of electric vehicle users to choose high-power charging in specific situations (e.g., peak hours, emergency needs, etc.). This factor can be dynamically adjusted through historical data analysis, user behavior pattern recognition, or machine learning models.

[0129] The number of vehicles simultaneously engaging in high-power energy replenishment in step C2 is determined by a comprehensive assessment of the number of electric vehicles with low battery levels in the surrounding area, pedestrian density index, and commercial activity level. For example, a high pedestrian density index and high commercial activity level indicate high activity in the area, increasing the demand and likelihood of electric vehicle users engaging in high-power energy replenishment. Therefore, given the same number of low-battery electric vehicles, it is expected that more vehicles will choose to engage in high-power energy replenishment simultaneously. This number can be calculated using a multivariate regression model or a rule-based inference system.

[0130] The predicted power load in step C3 is obtained by multiplying the number of vehicles simultaneously providing high-power energy replenishment, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment, or by using a more complex model for comprehensive calculation. For example, the predicted power load can be calculated as: the number of vehicles simultaneously providing high-power energy replenishment. Theoretical maximum energy replenishment power per electric vehicle The preference intensity factor for high-power energy replenishment. This calculation aims to simulate the total energy replenishment demand that may arise in a high-power energy replenishment cluster within a specific time period;

[0131] Steps C1 to C3 are specific implementation methods for obtaining the predicted power load in step S3. They involve introducing multi-dimensional data to refine the calculation of the predicted power load, thus solving the problem of coarse estimation that may exist in traditional methods when predicting the load of high-power energy replenishment clusters. Specifically, firstly, by obtaining the number of electric vehicles with low battery levels around the prediction area, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment, basic data is provided for subsequent load prediction. Secondly, by combining the number of low-battery electric vehicles with the pedestrian density index and commercial activity intensity, it is possible to more accurately estimate how many vehicles will actually choose to simultaneously replenish high-power energy at a specific time and location. This is because pedestrian density and commercial activity intensity can reflect the activity level and potential charging demand intensity of the area, thus correcting the bias of estimation based solely on the number of vehicles. Finally, multiplying these corrected numbers of vehicles simultaneously replenishing high-power energy with the theoretical maximum power of a single vehicle and the preference intensity factor yields a predicted power load that more closely reflects the actual situation. This multi-factor comprehensive approach allows the prediction results to more fully reflect the actual energy replenishment needs, avoiding prediction errors caused by insufficient consideration of a single factor.

[0132] Through the above technical solution, this application can significantly improve the accuracy and reliability of traffic energy load demand analysis. Specifically, by obtaining refined forecast power load, the instantaneous impact of high-power energy replenishment clusters on the power grid can be assessed more accurately, thus providing a more solid data foundation for risk warning and dispatch recommendations. Compared with load forecasting methods based solely on experience or simple statistics, this application introduces multiple factors such as vehicle number, vehicle power, user preferences, pedestrian density, and commercial activity intensity, making the forecast results closer to the actual situation and effectively avoiding the risk of overestimating or underestimating the load. Therefore, power grid load management can be carried out more effectively, reducing power grid overload or resource waste caused by sudden high-power energy replenishment demand, and improving the operating efficiency and stability of the energy system.

[0133] In some preferred embodiments, a specific example is given below. Suppose that in a certain prediction area, a third-party judgment identifies 50 high-power electric vehicles with low battery status in the vicinity. The average theoretical maximum energy replenishment power of these vehicles is 100kW. Through historical data analysis and machine learning models, the preference intensity factor for high-power energy replenishment in the current time period is determined to be 0.8.

[0134] Furthermore, by obtaining the pedestrian density index of the predicted area as "high" and the commercial activity intensity as "very active", the system calculates, based on a preset algorithm model (e.g., a regression model trained on historical data), that among the 50 low-battery electric vehicles, it is expected that 30 vehicles will choose to simultaneously replenish their high-power energy.

[0135] Therefore, the predicted power load will be calculated as follows:

[0136] Predicted power load Meanwhile, the number of vehicles replenished with high-power energy Theoretical maximum energy replenishment power per electric vehicle The intensity factor of preference for high-power energy replenishment;

[0137] Predicted power load 30 vehicles 100kW / vehicle 0.8 = 2400kW;

[0138] In this way, the system can obtain a specific and highly confident predicted power load of 2400kW. This load value will be used for subsequent instantaneous impact calculations and risk assessments, thereby providing an accurate reference for power grid dispatch.

[0139] like Figure 5 As shown, preferably, the predicted power load in the high-power energy replenishment cluster and the real-time power load within the predicted area are obtained, and the predicted power load and the real-time power load are simulated and superimposed to calculate the instantaneous impact, including the following steps:

[0140] D1. Obtain real-time operational data and design capacity data of the end-point energy distribution network within the prediction area;

[0141] D2. Overlay the predicted power load onto the end-point energy distribution network within the prediction region to obtain the sum of the predicted power load and the real-time power load;

[0142] D31. Obtain the voltage drop percentage based on the predicted power load, line impedance, and rated voltage;

[0143] D32. Based on the sum of the predicted power load and the real-time power load, and the real-time ambient temperature, obtain the predicted maximum temperature rise.

[0144] D33. Obtain the predicted line current based on the sum of the predicted power load and the real-time power load, and the real-time line voltage;

[0145] D4. The voltage drop percentage, the predicted maximum temperature rise, and the predicted line current are considered as instantaneous effects;

[0146] The real-time operating data includes: real-time power load, real-time ambient temperature, and real-time line voltage;

[0147] Design load data includes: rated voltage and line impedance.

[0148] The end-point energy distribution network in step D1 refers to the local power grid infrastructure that provides power supply to the predicted area, such as substations, distribution lines, transformers, etc.; real-time operating data refers to the dynamic operating parameters of the power grid at the current moment, specifically including real-time power load, real-time ambient temperature, and real-time line voltage. These data reflect the immediate state of the power grid; design carrying capacity data refers to the inherent attributes and design parameters of the power grid infrastructure, specifically including rated voltage and line impedance. These data define the carrying capacity and electrical characteristics of the power grid.

[0149] Step D2 involves overlaying the predicted power load onto the end-point energy distribution network within the prediction region to obtain the sum of the predicted power load and the real-time power load. This step aims to simulate the total power load that the grid needs to carry when a high-power energy supplement cluster forms.

[0150] The voltage drop percentage in step D31 is an important indicator for measuring the voltage stability of the power grid. Its calculation is usually based on Kirchhoff's law and Ohm's law of the power grid, reflecting the degree of voltage drop at the end of the power grid relative to the rated voltage under the influence of new loads.

[0151] The predicted maximum temperature rise in step D32 is used to assess the thermal stress of power grid equipment (such as cables, transformers, etc.) under the influence of total load and ambient temperature in order to determine whether there is a risk of overheating.

[0152] The predicted line current in step D33 is a key parameter for assessing the current-carrying capacity of the power grid line, used to determine whether the line will be overloaded due to excessive current.

[0153] Step D4 considers the voltage drop percentage, predicted maximum temperature rise, and predicted line current as instantaneous effects. These parameters comprehensively reflect the immediate impact and potential risks of high-power energy replenishment clusters on the grid's operating status.

[0154] Steps D1 to D4 detail the implementation of step S3, providing a foundation for subsequent load impact assessment by acquiring real-time operational and design load data of the end-point energy distribution network. By overlaying the predicted power load with the real-time power load, the total power load borne by the end-point energy distribution network during a specific time period when a high-power energy supplement cluster forms can be simulated. Based on this total power load and the network's electrical characteristics, the voltage drop percentage, predicted maximum temperature rise, and predicted line current can be calculated. These parameters are key indicators for assessing grid stability and security, collectively constituting a quantitative description of the instantaneous impact on the grid, thus providing data support for subsequent risk assessment and dispatch recommendations.

[0155] The aforementioned technical solutions enable a multi-dimensional and refined assessment of the potential instantaneous impact of high-power energy replenishment clusters on transportation energy load. Specifically, calculating the voltage drop percentage effectively evaluates grid voltage stability; obtaining the predicted maximum temperature rise accurately predicts equipment heat load and potential overheating risks; and calculating the predicted line current determines whether the line's current-carrying capacity meets requirements. These detailed indicators collectively constitute a comprehensive characterization of the instantaneous impact, allowing for more accurate and timely risk warnings and dispatch recommendations. This effectively avoids problems such as localized grid overload, voltage instability, or equipment damage caused by high-power energy replenishment clusters, ensuring the reliability and security of energy supply.

[0156] This application further proposes the following steps for determining whether the instantaneous impact exceeds a preset risk threshold, and if so, issuing a risk warning and providing scheduling suggestions:

[0157] Determine whether the voltage drop percentage exceeds the preset voltage stability risk threshold and record it as the fifth judgment result;

[0158] Determine whether the predicted maximum temperature rise exceeds the preset temperature risk threshold and record it as the sixth judgment result.

[0159] Determine whether the predicted line current exceeds the rated current, and record this as the seventh judgment result;

[0160] Based on the results of the fifth, sixth, and seventh judgments, a risk warning is issued and corresponding scheduling suggestions are provided.

[0161] The design load data also includes: rated current.

[0162] Specifically, the fifth judgment result refers to assessing the percentage voltage drop to determine whether it exceeds a preset voltage stability risk threshold. This preset voltage stability risk threshold can be set according to power grid operation specifications, equipment withstand capabilities, and system stability requirements; for example, it can be set as a drop of 5% or 10% of the line's rated voltage. Its purpose is to ensure stable operation of the power grid voltage and avoid equipment failure or system collapse due to excessively low voltage. The sixth judgment result refers to assessing the predicted maximum temperature rise to determine whether it exceeds a preset temperature risk threshold. This preset temperature risk threshold is usually determined based on the heat resistance rating and safe operating temperature limit of the insulation materials of power equipment such as cables and transformers; for example, it can be set to 70℃ or 80℃. Its purpose is to prevent power equipment from aging prematurely, reducing its lifespan, or even causing safety accidents such as fires due to overheating. The seventh judgment result refers to assessing the predicted line current to determine whether it exceeds the rated current. The rated current is the maximum current value that a power line or equipment can withstand for a long period under normal operating conditions, usually provided by the equipment manufacturer or determined according to design standards. Its purpose is to prevent damage to the line or equipment due to long-term overload operation.

[0163] The seventh judgment result mentioned above is based on the design load data, which includes the rated current in addition to the original rated voltage and line impedance. The rated current, as part of the design load data, provides a crucial reference for determining whether the line is overloaded.

[0164] The above steps are the specific implementation details of step S4. They involve refining the instantaneous impact into three specific indicators: voltage drop percentage, predicted maximum temperature rise, and predicted line current. These indicators are then compared with preset voltage stability risk thresholds, preset temperature risk thresholds, and rated current, respectively. This allows for a multi-dimensional and refined assessment of potential power grid risks. This multi-indicator comprehensive judgment mechanism makes risk warnings more comprehensive and accurate, avoiding the potential bias of judging by a single indicator and ensuring a complete understanding of the power grid's operating status.

[0165] The aforementioned technical solution enables a more accurate and comprehensive risk assessment of the instantaneous impact on the power grid caused by transportation energy load demand. Compared to simply judging whether a single, comprehensive instantaneous impact exceeds a preset risk threshold, this solution, by separately considering key operating parameters such as voltage stability, equipment temperature rise, and line current, can identify potential power grid operation risks earlier and more accurately, such as specific problems like voltage instability, equipment overheating, or line overload. Consequently, the risk warning information issued will be more targeted, and the dispatching recommendations provided will be able to more accurately and effectively guide power grid management departments to take preventative or mitigation measures, thereby significantly improving the reliability, safety, and stability of power grid operation.

[0166] In some embodiments described above in this application, a method for obtaining predicted power load is proposed. However, in its implementation, this method mainly relies on relatively static or aggregated macroscopic data such as the number of vehicles, theoretical maximum energy replenishment power, pedestrian density index, and commercial activity intensity for prediction. This prediction method may fail to fully consider the dynamic behavioral deviations of individual electric vehicles during actual operation due to changes in the external environment or adjustments in driver behavior. For example, vehicles may deviate from their expected energy replenishment path due to traffic congestion, emergencies, or temporary changes in plans, resulting in a discrepancy between the actual energy replenishment demand and the initial prediction. If the above problems are not addressed, the accuracy of predicted power load may be affected, thereby impacting the timeliness of risk warnings and the effectiveness of scheduling recommendations.

[0167] like Figure 6 As shown, this application further proposes, after obtaining the aforementioned predicted power load, the following steps are also included:

[0168] E1. Obtain the actual movement trajectory of each high-power electric vehicle with low battery status around the prediction area, and construct the expected movement path for each electric vehicle based on the initial intent.

[0169] E2 compares the actual movement trajectory and expected movement path of each electric vehicle in real time, detects and identifies the behavioral deviation of each electric vehicle caused by environmental discomfort, and classifies it into different behavioral deviation types.

[0170] E3. Obtain the intensity and duration of current environmental discomfort, and generate behavioral response correction factors based on the type of behavioral deviation;

[0171] E4. Adjust the number of vehicles simultaneously receiving high-power energy replenishment and the predicted power load based on the behavioral response correction factor, and update the risk warning information based on the adjusted number of vehicles simultaneously receiving high-power energy replenishment and the adjusted predicted power load.

[0172] The actual movement trajectory in step E1 can be obtained in real time through vehicle global positioning system (GPS) data, on-board sensor data, or data interaction with traffic management system; the expected movement path can be generated based on historical driving data, user preset destination, navigation system planned path, or combined with artificial intelligence algorithm to predict driving behavior; the initial intent refers to the intention set by the driver or autonomous driving system to go to the energy replenishment station before the vehicle enters the predicted area or at a specific time.

[0173] Environmental discomfort in step E2 may include, but is not limited to, traffic congestion, severe weather (such as heavy rain or snow), road construction, unexpected accidents, or drivers changing their plans at the last minute. A behavioral deviation is identified when there is a significant difference between the actual movement trajectory and the expected movement path. These behavioral deviations can be categorized into different types based on their nature and severity, such as "turning to another charging station," "abandoning charging," "delaying charging," or "changing destination."

[0174] The intensity of environmental discomfort in step E3 can be quantified as traffic congestion index, weather warning level, accident impact range, etc., while the duration refers to the expected duration of the discomfort. The behavioral response correction factor is a numerical value or function used to quantify the impact of a specific behavioral deviation type on the vehicle's willingness and behavior to recharge energy under a specific intensity and duration of environmental discomfort. For example, if the deviation type of "abandoning charging" is identified and the intensity of environmental discomfort is high, the correction factor may significantly reduce the probability of the vehicle recharging energy.

[0175] Step E4 involves adjusting the number of vehicles simultaneously receiving high-power energy replenishment and the predicted power load based on a behavior response correction factor. This correction process can involve applying the behavior response correction factor to the originally calculated number of vehicles and power load, for example, through multiplication or weighted averaging. Therefore, based on the corrected number of vehicles simultaneously receiving high-power energy replenishment and the corrected predicted power load, the risk warning information is updated. This means that when the actual behavior of vehicles deviates from expectations, the system can promptly adjust its prediction of future power load and update any potential risk warnings accordingly, thereby providing more accurate scheduling recommendations.

[0176] Steps E1 to E4 detail the implementation of steps C3, effectively addressing the limitations of traditional methods in predicting power load by introducing a dynamic monitoring and correction mechanism for individual electric vehicle behavior. Specifically, by acquiring the actual movement trajectory of each electric vehicle and comparing it in real time with the expected movement path based on the initial intent, behavioral deviations caused by changes in the external environment or adjustments in internal decisions can be detected promptly. These deviations are key factors leading to discrepancies between actual energy replenishment demand and predicted values. Furthermore, by categorizing these behavioral deviations and generating behavioral response correction factors based on the intensity and duration of current environmental discomfort, the assessment of vehicle energy replenishment intentions becomes more refined and dynamic. For example, when a large number of vehicles are detected deviating from their paths to charging stations due to traffic congestion, the correction factor correspondingly reduces the likelihood of these vehicles replenishing energy at high power within the predicted time period. Finally, these correction factors are used to adjust the number of vehicles simultaneously replenishing energy at high power and the predicted power load, enabling the prediction results to more accurately reflect actual energy demand and avoiding prediction biases caused by changes in vehicle behavior.

[0177] Through the above technical solution, this application can significantly improve the accuracy and real-time performance of traffic energy load demand analysis. Compared with basic solutions that rely solely on static or aggregated data for prediction, this application, by introducing dynamic monitoring and correction of individual electric vehicle behavior, can promptly capture and quantify deviations in energy replenishment behavior caused by environmental changes. Therefore, the calculation of predicted power load is no longer based on idealized assumptions but can be dynamically adjusted according to actual conditions, effectively reducing prediction errors. This more accurate prediction capability makes the risk warning information issued by the system more reliable and provides more targeted and timely scheduling suggestions. For example, when the actual load is predicted to be lower than expected, unnecessary grid resource reservations can be avoided; when the actual load is predicted to be higher than expected, measures can be taken in advance, such as guiding vehicles to other charging stations or activating backup power, thereby effectively avoiding grid overload risks and ensuring the stability and reliability of energy supply.

[0178] In some preferred embodiments, a specific example is given below. Suppose that in a prediction area of ​​a city, the system initially predicts that 50 high-power electric vehicles will need to refuel within the next hour, with a predicted power load of 5MW. However, after the prediction period begins, the system detects through real-time monitoring that a traffic accident has occurred in the area, causing severe congestion on the road leading to the main refueling station.

[0179] Specifically, the system obtained the actual movement trajectories of 20 electric vehicles, which were originally planned to go to the energy replenishment station but are now deviating from their expected paths, turning in other directions or remaining stationary. The system categorizes these deviations as either "delayed charging" or "turning to other charging stations." Simultaneously, the system determined the intensity of the current environmental discomfort (traffic accident) to be "severe congestion," with an estimated duration of 30 minutes. Based on a pre-set model, a behavioral response correction factor for the "delayed charging" type under the "severe congestion" environment is generated, for example, reducing the energy replenishment probability of these vehicles by 50%. For vehicles "turning to other charging stations," the correction factor may reduce their energy replenishment probability to 0% (within the predicted area).

[0180] Therefore, based on these behavioral response correction factors, the system adjusted the number of vehicles simultaneously providing high-power energy replenishment. For example, if 20 out of the originally projected 50 vehicles had a reduced probability of energy replenishment due to behavioral deviations, the actual number of vehicles expected to provide high-power energy replenishment might be reduced to 35 after the correction. Based on this, the predicted power load was also revised from 5MW to 3.5MW. The system then updated the risk warning information, changing the previously anticipated "medium load risk" to "low load risk," and accordingly adjusted the dispatch recommendations. For example, it canceled the planned startup of a backup generator unit, thus avoiding unnecessary resource waste while ensuring the stable operation of the power grid.

[0181] In some embodiments described above, the predicted power load is primarily estimated based on factors such as the number of vehicles, the theoretical maximum energy replenishment power, and macroscopic factors like pedestrian density and commercial activity intensity. However, in actual energy replenishment, microscopic factors such as the actual battery status of each electric vehicle and the local ambient temperature of the energy replenishment station can significantly affect the actual maximum energy replenishment power of the vehicle, leading to discrepancies between the predicted power load estimated based on theoretical values ​​and macroscopic data and the actual situation. Failure to address this issue may result in inaccurate predictions of future energy load, thereby affecting the accuracy of risk warnings and the effectiveness of scheduling recommendations. Therefore, this application further proposes a method to correct the predicted power load after acquisition by real-time monitoring of the electric vehicle's battery management system data and the local ambient temperature of the energy replenishment station, thereby improving the accuracy of the prediction.

[0182] like Figure 7 As shown, after obtaining the predicted power load, the following steps are also included:

[0183] F1. When each high-power electric vehicle with a low battery status in the vicinity of the prediction area connects to the energy replenishment station in the prediction area, the real-time communication data of the battery management system of each electric vehicle is obtained.

[0184] F2. Analyze the real-time communication data of the battery management system to obtain the actual battery temperature and actual maximum energy replenishment power of each electric vehicle;

[0185] F3. Obtain the local ambient temperature of the energy replenishment station within the prediction area, correlate the local ambient temperature with the actual battery temperature of each electric vehicle, and generate the reason for the energy replenishment power limitation.

[0186] F4. Based on the reasons for the energy replenishment power limitation and the actual maximum energy replenishment power of each electric vehicle, the predicted power load is corrected, and the risk warning information is updated based on the corrected predicted power load.

[0187] In step F1, when high-power electric vehicles with low battery levels in the surrounding area connect to an energy replenishment station within the prediction area, the system will actively or passively acquire real-time communication data from the battery management system of each electric vehicle. This real-time communication data can be understood as the real-time operating parameters provided by the battery management unit inside the electric vehicle, such as battery pack voltage, current, temperature, state of health (SOH), and state of charge (SOC). Its purpose is to obtain the real-time health status and performance parameters of the vehicle's battery.

[0188] The actual battery temperature in step F2 refers to the real-time temperature inside the battery pack, which directly affects the battery's charging and discharging performance and safety. The actual maximum energy replenishment power refers to the maximum charging power the battery can safely accept under the current battery state (such as temperature, SOC, SOH), which is usually lower than its theoretical maximum energy replenishment power. Its purpose is to identify the actual limiting factors affecting charging power.

[0189] The local ambient temperature in step F3 refers to the real-time ambient temperature around the energy replenishment station, which affects the heat dissipation performance of the energy replenishment equipment and the temperature changes of the electric vehicle battery. The local ambient temperature is correlated with the actual battery temperature of each electric vehicle; this means that these two temperature data are analyzed comprehensively to determine whether there is an energy replenishment power limitation due to excessively high or low temperatures. This generates the cause of the energy replenishment power limitation; for example, when the actual battery temperature or the local ambient temperature exceeds the safe range, it may trigger the power limiting strategy of the battery management system or the energy replenishment station.

[0190] Step F4 involves correcting the predicted power load based on the reasons for the energy replenishment power limitation and the actual maximum energy replenishment power of each electric vehicle. For example, if an electric vehicle's actual maximum energy replenishment power is found to be lower than the theoretical value due to excessively high battery temperature, its actual maximum energy replenishment power should be used instead of the theoretical maximum energy replenishment power when calculating the vehicle's contribution to the total load. Based on the corrected predicted power load, the risk warning information is updated to ensure the accuracy and timeliness of risk assessments and scheduling recommendations.

[0191] Steps F1 to F4 detail the implementation of steps C3. By introducing real-time communication data from the electric vehicle's battery management system and monitoring and analyzing the local ambient temperature of the energy replenishment station, they address the problem of traditional prediction methods failing to adequately consider actual charging limitations. Specifically, when an electric vehicle connects to the energy replenishment station, the system can acquire the actual battery temperature and maximum energy replenishment power of each vehicle in real time. This data reflects the battery's true performance under current operating conditions, avoiding the bias caused by relying solely on theoretical maximum power estimation. Simultaneously, by combining this with the local ambient temperature of the energy replenishment station, the impact of the charging environment on charging power can be more comprehensively assessed, thereby generating more accurate reasons for energy replenishment power limitations. It is precisely because of the introduction of this real-time, microscopic data that the predicted power load can be dynamically corrected based on actual conditions, thus more accurately reflecting potential future energy load demands.

[0192] Through the above technical solution, this application overcomes the potential bias in power load prediction in existing technologies. By acquiring real-time data from the battery management system of electric vehicles and the local ambient temperature of energy replenishment stations, and correcting the predicted power load accordingly, the prediction results are made closer to the actual situation. This correction mechanism significantly improves the accuracy of traffic energy load demand analysis, enabling more timely and accurate risk warnings and providing more reasonable and effective scheduling suggestions. Compared to relying solely on theoretical values ​​and macroscopic data for prediction, the solution in this application effectively avoids problems such as grid overload, waste of energy replenishment resources, or untimely scheduling caused by inaccurate predictions, further improving the precision of energy load management and the operational reliability of the system.

[0193] As a specific implementation method, a concrete example is given below. Suppose that within a certain prediction area, the system has preliminarily predicted, based on macroscopic data, that a high-power energy replenishment cluster will form within a certain future time period, and has calculated the preliminary predicted power load. At this time, three high-power electric vehicles, A, B, and C, successively connect to the energy replenishment station in this area.

[0194] For electric vehicle A, the system analyzes real-time communication data from its battery management system to determine that the actual battery temperature is 45℃ and the actual maximum energy replenishment power is 150kW. Meanwhile, the local ambient temperature at the energy replenishment station is 35℃. Because the actual battery temperature is slightly higher, the system determines that there is a minor power limitation.

[0195] For electric vehicle B, the system analyzes its battery management system's real-time communication data and finds that its actual battery temperature is 25℃ and its actual maximum energy replenishment power is 200kW. The local ambient temperature of the energy replenishment station is 35℃. The system determines that there is no obvious cause for the power limitation.

[0196] For electric vehicle C, the system analyzes its battery management system's real-time communication data and finds that its actual battery temperature is 55℃, and its actual maximum energy replenishment power is only 100kW. The local ambient temperature of the energy replenishment station is 35℃. The system determines that there is a significant cause for the power limitation, such as battery overheat protection.

[0197] Without the proposed solution, the system might still predict the load based on the theoretical maximum energy replenishment power of 200kW per vehicle. However, with the proposed solution, the system will revise the initial predicted power load based on the actual maximum energy replenishment power of each vehicle (150kW for A, 200kW for B, and 100kW for C) and power limitations. For example, if the initial predicted total load of the three vehicles is 600kW, the revised load becomes 150kW + 200kW + 100kW = 450kW. Based on the revised predicted power load of 450kW, the system will update the risk warning information, such as adjusting a previously issued "high-risk" warning to "medium-risk" or "low-risk," and providing corresponding dispatch suggestions. This avoids overestimating or underestimating the grid load, improving the accuracy of predictions and the reliability of dispatch decisions.

[0198] like Figure 8 As shown in the illustration, this application also discloses a traffic energy load demand analysis system, applied in the field of energy load analysis, comprising:

[0199] The prediction area parameter acquisition module is used to obtain the usage status of energy replenishment stations within the prediction area according to a preset data transmission protocol, and to obtain the pedestrian density index, commercial activity heat and high-power vehicle power status respectively.

[0200] The high-power energy replenishment cluster formation module is used to define that a high-power energy replenishment cluster will be formed in the predicted area within a preset time period when the usage status of energy replenishment stations, the population density index, the commercial activity intensity, and the high-power vehicle power status in the predicted area all meet preset conditions.

[0201] The instantaneous impact acquisition module is used to acquire the predicted power load in the high-power energy replenishment cluster and the real-time power load in the prediction area, simulate and superimpose the predicted power load and the real-time power load, and calculate and acquire the instantaneous impact.

[0202] The risk warning and scheduling module is used to determine whether the instantaneous impact exceeds the preset risk threshold. If so, it issues a risk warning and provides scheduling suggestions.

[0203] The traffic energy load demand analysis system proposed in this application aims to achieve accurate prediction and management of urban traffic energy load through a modular approach, especially in the context of the increasing prevalence of electric vehicles and the growing demand for high-power energy replenishment. The system dynamically collects multi-dimensional data through a regional parameter acquisition module, intelligently identifies potential high-power energy replenishment clusters through a high-power energy replenishment cluster formation module, assesses their potential impact on the energy distribution network through a transient impact acquisition module, and finally issues timely warnings and provides scheduling suggestions through a risk warning and scheduling module. Therefore, this system effectively solves the problem that traditional methods struggle to accurately capture localized, transient, and high-intensity energy replenishment peaks, providing forward-looking technical support for refined scheduling of energy distribution networks, dynamic optimization of energy replenishment infrastructure, and early warning of potential risks.

[0204] The prediction area parameter acquisition module is configured to acquire the usage status of energy replenishment stations within the prediction area according to a preset data transmission protocol, and to acquire the pedestrian density index, commercial activity intensity, and high-power vehicle battery status, respectively. The specific methods for acquiring the usage status of energy replenishment stations, pedestrian density index, commercial activity intensity, and high-power vehicle battery status have already been described in the above embodiments and will not be repeated here. It is important to emphasize that this module can be a standalone hardware unit, such as a data acquisition server or an edge computing device, which integrates multiple sensor interfaces and communication modules to receive data in real time from energy replenishment stations, mobile communication networks, social media platforms, and vehicle data platforms. As a preferred implementation, this module can also be deployed in software on a cloud server, interacting with various data sources through API interfaces to achieve remote data acquisition and preprocessing.

[0205] The high-power energy replenishment cluster formation module is configured to define the formation of a high-power energy replenishment cluster within a preset time period in the predicted area when the usage status of energy replenishment stations, pedestrian density index, commercial activity intensity, and high-power vehicle battery status all meet preset conditions. The preset conditions and logic for determining the formation of a high-power energy replenishment cluster have already been described in the above embodiments and will not be repeated here. It is important to emphasize that this module can be a software service running on a server, receiving real-time data from the predicted area parameter acquisition module and analyzing it according to preset judgment logic. For example, this module can use a rule-based expert system or machine learning model to perform pattern recognition on the input data to accurately determine the formation of a high-power energy replenishment cluster.

[0206] The instantaneous impact acquisition module is configured to acquire the predicted power load in the high-power energy replenishment cluster and the real-time power load within the prediction area, simulate and superimpose the predicted power load and the real-time power load, and calculate and acquire the instantaneous impact. The acquisition methods for the predicted power load and real-time power load, as well as the calculation methods for the instantaneous impact, have already been described in the above embodiments and will not be repeated here. It is important to emphasize that this module can be a high-performance computing unit, such as a server equipped with a dedicated computing chip, used to perform complex load superposition simulations and grid parameter calculations. It can integrate grid simulation software or customized algorithm libraries to ensure the accuracy and real-time performance of the calculation results.

[0207] The risk warning and scheduling module is configured to determine whether the instantaneous impact exceeds a preset risk threshold. If so, it issues a risk warning and provides scheduling suggestions. The judgment criteria for the risk threshold and the specific content of the risk warning and scheduling suggestions have already been described in the above implementation, and will not be repeated here. It is important to emphasize that this module can be a decision support system that receives the calculation results from the instantaneous impact acquisition module and compares them with the preset risk threshold. When a risk is detected, this module can automatically generate a warning and send it to relevant management personnel through various channels (such as SMS, email, application push, or control center display). Simultaneously, this module can also automatically generate and recommend optimal scheduling suggestions based on a preset scheduling strategy library, such as adjusting the power output of energy replenishment stations, activating backup energy sources, or notifying the power grid dispatch center to perform load transfer, to effectively mitigate potential risks.

[0208] The transportation energy load demand analysis system proposed in this application, compared to traditional methods, has a core innovation in its modular system architecture, enabling dynamic and refined perception and prediction of urban transportation energy load. Traditional methods primarily rely on aggregating vehicle energy consumption data for macro-level prediction, which struggles to address the localized, transient, and high-intensity load impacts caused by high-power energy replenishment from electric vehicles. This system, however, utilizes a prediction area parameter acquisition module to collect multi-dimensional data in real time; a high-power energy replenishment cluster formation module to intelligently identify opportunistic high-power energy replenishment clusters; a transient impact acquisition module to accurately assess their transient impact on the power grid; and a risk warning and dispatch module to promptly issue warnings and provide dispatch suggestions. Therefore, this system can proactively identify and mitigate potential risks such as power grid overload and voltage drops, significantly improving the stability and reliability of the urban energy distribution network and providing a more advanced and reliable solution for smart city energy management.

[0209] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, and can be electrical, mechanical, or other forms.

[0210] In addition, each functional module in the various embodiments of this application can be fully integrated into a processor, or each module can be a separate device, or two or more modules can be integrated into a device; each functional module in the various embodiments of this application can be implemented in hardware or in the form of hardware plus software functional units.

[0211] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, they perform the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0212] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0213] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0214] The foregoing has provided a detailed description of a traffic energy load demand analysis method and system provided in this application. The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for analyzing traffic energy load demand, applied in the field of energy load analysis, characterized in that, Includes the following steps: Within the predicted area, the usage status of energy replenishment stations is obtained according to the preset data transmission protocol, and the pedestrian density index, commercial activity intensity, and high-power vehicle battery status are obtained respectively. When the usage status of the energy replenishment station, the pedestrian density index, the commercial activity intensity, and the high-power vehicle battery status within the prediction area all meet preset conditions, it is defined that a high-power energy replenishment cluster will be formed in the prediction area within a preset time period. The predicted power load in the high-power energy replenishment cluster is obtained according to a preset method, and the real-time power load in the predicted area is obtained. The predicted power load and the real-time power load are simulated and superimposed to calculate the instantaneous impact. Determine whether the instantaneous impact exceeds a preset risk threshold; if so, issue a risk warning and provide scheduling suggestions. After obtaining the predicted power load, the method further includes the following steps: Obtain the actual movement trajectory of each high-power electric vehicle with a low battery status around the prediction area, and construct the expected movement path for each electric vehicle based on the initial intent. The actual movement trajectory and the expected movement path of each electric vehicle are compared in real time to detect and identify the behavioral deviation of each electric vehicle caused by environmental discomfort and classify it into different behavioral deviation types. Obtain the current environmental discomfort intensity and duration, and generate a behavior response correction factor based on the behavior deviation type; The number of vehicles simultaneously receiving high-power energy replenishment and the predicted power load are adjusted according to the behavioral response correction factor. The risk warning information is then updated based on the adjusted number of vehicles simultaneously receiving high-power energy replenishment and the adjusted predicted power load.

2. A method for analyzing traffic energy load demand, applied in the field of energy load analysis, characterized in that, Includes the following steps: Within the predicted area, the usage status of energy replenishment stations is obtained according to the preset data transmission protocol, and the pedestrian density index, commercial activity intensity, and high-power vehicle battery status are obtained respectively. When the usage status of the energy replenishment station, the pedestrian density index, the commercial activity intensity, and the high-power vehicle battery status within the prediction area all meet preset conditions, it is defined that a high-power energy replenishment cluster will be formed in the prediction area within a preset time period. The predicted power load in the high-power energy replenishment cluster is obtained according to a preset method, and the real-time power load in the predicted area is obtained. The predicted power load and the real-time power load are simulated and superimposed to calculate the instantaneous impact. Determine whether the instantaneous impact exceeds a preset risk threshold; if so, issue a risk warning and provide scheduling suggestions. After obtaining the predicted power load, the following steps are also included: When each high-power electric vehicle with a low battery status in the vicinity of the prediction area connects to the energy replenishment station in the prediction area, real-time communication data of the battery management system of each electric vehicle is obtained. The battery management system's real-time communication data is analyzed to obtain the actual battery temperature and actual maximum energy replenishment power for each electric vehicle. The local ambient temperature of the energy replenishment station within the prediction area is obtained, and the local ambient temperature is correlated with the actual battery temperature of each electric vehicle to generate the cause of the energy replenishment power limitation. Based on the reasons for the energy replenishment power limitation and the actual maximum energy replenishment power of each electric vehicle, the predicted power load is corrected, and the risk warning information is updated based on the corrected predicted power load.

3. The traffic energy load demand analysis method as described in claim 1 or 2, characterized in that, The pedestrian density index is obtained in the following way: Obtain the number of active users and wireless network connected devices within the predicted area; The population density index within the predicted area is obtained by combining the sum of the number of active users and the number of wireless network connected devices with the predicted area area.

4. The traffic energy load demand analysis method as described in claim 1 or 2, characterized in that, The popularity of the aforementioned business activities was obtained through the following methods: Obtain real-time check-in volume related to the predicted region on social media platforms; Obtain real-time data on changes in the number and value of transactions within the prediction area; The popularity of the business activity is calculated by adding weights to the real-time check-in volume, the real-time transaction volume, and the transaction amount change data, and then summing them.

5. The traffic energy load demand analysis method as described in claim 1 or 2, characterized in that, When the usage status of the energy replenishment stations, the pedestrian density index, the commercial activity intensity, and the battery status of high-power vehicles within the prediction area all meet preset conditions, it is defined that a high-power energy replenishment cluster will form in the prediction area within a preset time period, including the following steps: Based on the usage status of the energy replenishment stations within the predicted area, determine whether the predicted area is a traditional energy replenishment hotspot area, and record it as the first judgment result; If the first judgment result is negative, determine whether the pedestrian density index of the predicted area exceeds the pedestrian density index threshold within a preset time period, and record it as the second judgment result. Determine whether there are more than a preset number of electric vehicles with low battery status in the vicinity of the prediction area, and record this as the third determination result. If the popularity of the business activities within the predicted area exceeds a preset popularity threshold, it is recorded as the fourth judgment result. When the second, third, and fourth judgment results are all yes, the prediction area is defined to form a high-power energy replenishment cluster within a preset time period.

6. The traffic energy load demand analysis method as described in claim 5, characterized in that, The step of obtaining the predicted power load in the high-power energy replenishment cluster according to a preset method includes the following steps: The number of electric vehicles with low battery status in the vicinity of the prediction area, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment are obtained. Based on the number of electric vehicles with low battery status in the surrounding area, the pedestrian density index, and the commercial activity intensity, the number of vehicles that can simultaneously replenish high-power energy is obtained. The predicted power load is obtained based on the number of vehicles simultaneously receiving high-power energy replenishment, the theoretical maximum energy replenishment power of each electric vehicle, and the preference intensity factor for high-power energy replenishment.

7. The traffic energy load demand analysis method as described in claim 1 or 2, characterized in that, The process of obtaining the predicted power load in the high-power energy replenishment cluster and the real-time power load within the predicted area, simulating and superimposing the predicted power load and the real-time power load, and calculating the instantaneous impact includes the following steps: Obtain real-time operational data and design capacity data of the end-point energy distribution network within the predicted area; The predicted power load is superimposed onto the end-point energy distribution network within the prediction area to obtain the sum of the predicted power load and the real-time power load; The voltage drop percentage is obtained based on the predicted power load, line impedance, and rated voltage. The predicted maximum temperature rise is obtained based on the sum of the predicted power load and the real-time power load, and the real-time ambient temperature. The predicted line current is obtained based on the sum of the predicted power load and the real-time power load, and the real-time line voltage. The voltage drop percentage, the predicted maximum temperature rise, and the predicted line current are used as the instantaneous effects. The real-time operating data includes: the real-time power load, the real-time ambient temperature, and the real-time line voltage; The design load data includes: the rated voltage and the line impedance.

8. The traffic energy load demand analysis method as described in claim 7, characterized in that, The step of determining whether the instantaneous impact exceeds a preset risk threshold, and if so, issuing a risk warning and providing scheduling suggestions, includes the following steps: Determine whether the voltage drop percentage exceeds a preset voltage stability risk threshold, and record it as the fifth determination result; Determine whether the predicted maximum temperature rise exceeds the preset temperature risk threshold, and record it as the sixth determination result; Determine whether the predicted line current exceeds the rated current, and record it as the seventh determination result; Based on the fifth, sixth, and seventh judgment results, a risk warning is issued and corresponding scheduling suggestions are provided. The design load data also includes the rated current.

9. A traffic energy load demand analysis system, applied in the field of energy load analysis, characterized in that, include: The prediction area parameter acquisition module is used to obtain the usage status of energy replenishment stations within the prediction area according to a preset data transmission protocol, and to obtain the pedestrian density index, commercial activity heat and high-power vehicle power status respectively. A high-power energy replenishment cluster formation module is used to define that a high-power energy replenishment cluster will be formed in the predicted area within a preset time period when the usage status of the energy replenishment station, the pedestrian density index, the commercial activity heat and the high-power vehicle power status in the predicted area all meet preset conditions. The instantaneous impact acquisition module is used to acquire the predicted power load in the high-power energy replenishment cluster according to a preset method, acquire the real-time power load in the prediction area, simulate and superimpose the predicted power load and the real-time power load, and calculate and acquire the instantaneous impact. The risk warning and scheduling module is used to determine whether the instantaneous impact exceeds a preset risk threshold. If so, it issues a risk warning and provides scheduling suggestions. The behavior correction module is used to obtain the actual movement trajectory of each electric vehicle with low battery status in the surrounding area of ​​the high-power vehicle after obtaining the predicted power load, and construct the expected movement path based on the initial intention for each electric vehicle; compare the actual movement trajectory and the expected movement path of each electric vehicle in real time, detect and identify the behavior deviation of each electric vehicle caused by environmental discomfort, and classify it into different behavior deviation types. Obtain the current environmental discomfort intensity and duration, and generate a behavior response correction factor based on the behavior deviation type; The number of vehicles simultaneously receiving high-power energy replenishment and the predicted power load are adjusted according to the behavioral response correction factor. The risk warning information is then updated based on the adjusted number of vehicles simultaneously receiving high-power energy replenishment and the adjusted predicted power load.

10. A traffic energy load demand analysis system, applied in the field of energy load analysis, characterized in that, include: The prediction area parameter acquisition module is used to obtain the usage status of energy replenishment stations within the prediction area according to a preset data transmission protocol, and to obtain the pedestrian density index, commercial activity heat and high-power vehicle power status respectively. A high-power energy replenishment cluster formation module is used to define that a high-power energy replenishment cluster will be formed in the predicted area within a preset time period when the usage status of the energy replenishment station, the pedestrian density index, the commercial activity heat and the high-power vehicle power status in the predicted area all meet preset conditions. The instantaneous impact acquisition module is used to acquire the predicted power load in the high-power energy replenishment cluster according to a preset method, acquire the real-time power load in the prediction area, simulate and superimpose the predicted power load and the real-time power load, and calculate and acquire the instantaneous impact. The risk warning and scheduling module is used to determine whether the instantaneous impact exceeds a preset risk threshold. If so, it issues a risk warning and provides scheduling suggestions. The battery correction module is used to, after obtaining the predicted power load, acquire real-time communication data of the battery management system of each electric vehicle when a high-power electric vehicle with a low battery status in the vicinity of the prediction area connects to the energy replenishment station in the prediction area; parse the real-time communication data of the battery management system to obtain the actual battery temperature and actual maximum energy replenishment power of each electric vehicle; acquire the local ambient temperature of the energy replenishment station in the prediction area, correlate the local ambient temperature with the actual battery temperature of each electric vehicle to generate a reason for energy replenishment power limitation; correct the predicted power load based on the reason for energy replenishment power limitation and the actual maximum energy replenishment power of each electric vehicle; and update the risk warning information based on the corrected predicted power load.

Images