Charging and discharging resource prediction method, device and equipment based on user travel characteristics

Abstract

The invention discloses a charge and discharge resource prediction method, device and equipment based on user travel characteristics, and relates to the technical field of power resource scheduling, the method comprises the following steps: obtaining a prediction scene and a dynamic map of the prediction scene, the dynamic map comprising a plurality of function areas; based on a preset electric vehicle travel model and a dynamic map, obtaining a driving behavior of the user in the prediction scene; based on the driving behavior and battery characteristic parameters of the vehicle driven by the user, predicting charging and discharging power boundaries in different time periods; and aggregating the charging and discharging power boundaries of all vehicles in the same time period and the functional area to obtain the space-time distribution of the charging and discharging resources in the prediction scene. Therefore, more reliable and finer data support is provided for load regulation and control, charging facility planning and vehicle network interaction strategy making of the power grid side, prediction deviation of the electric vehicle charging and discharging resources is reduced, and the accuracy of time-space distribution testing of the electric vehicle charging and discharging resources is improved.

Description

Technical Field

[0001] This application relates to the field of power resource dispatching technology, and in particular to a method, apparatus and equipment for predicting charging and discharging resources based on user travel characteristics. Background Technology

[0002] With the advancement of dual-carbon goals, the number of electric vehicles is growing rapidly. A large number of electric vehicles are connected to the power grid, which not only brings new electricity load to the grid, but also is regarded as a potential distributed flexible regulation resource because electric vehicles have energy storage attributes.

[0003] Currently, the prediction of electric vehicle charging and discharging resources mainly relies on the user's vehicle's power consumption per unit distance and driving range, combined with psychological factors such as the user's anxiety about charging costs and preferences to predict the vehicle's charging and discharging load. However, current prediction methods do not incorporate dynamic maps and the characteristics of electric vehicles, leading to biases in the prediction results.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, and device for predicting charging and discharging resources based on user travel characteristics, aiming to solve the technical problem that current prediction methods do not combine dynamic maps and the characteristics of electric vehicles, resulting in deviations in prediction results.

[0006] To achieve the above objectives, this application proposes a method for predicting charging and discharging resources based on user travel characteristics. The method includes: Obtain the predicted scene and a dynamic map of the predicted scene, the dynamic map including multiple functional areas; Based on the preset electric vehicle travel model and the dynamic map, the user's driving behavior in the predicted scenario is obtained; Based on the driving behavior and the battery characteristic parameters of the user's vehicle, the charging and discharging power boundaries at different time periods are predicted. By aggregating the charging and discharging power boundaries of all vehicles within the same time period and functional area, the spatiotemporal distribution of charging and discharging resources in the predicted scenario is obtained.

[0007] In one embodiment, the step of obtaining the user's driving behavior in the predicted scenario based on a preset electric vehicle travel model and the dynamic map includes: Based on a preset electric vehicle travel model, predict the travel trajectory of the vehicle in the predicted scenario; Based on the dynamic map, congestion analysis is performed for each travel period to obtain the degree of impact of road conditions on user travel. The travel trajectory is corrected based on the degree of impact to obtain the user's driving behavior in the predicted scenario. The driving behavior includes the travel trajectory and the user's travel intention.

[0008] In one embodiment, before the step of predicting the travel trajectory of vehicles in the predicted scenario based on a preset electric vehicle travel model, the following steps are included: Obtain historical vehicle driving data; Analyze the probabilistic relationship between each historical vehicle driving data and travel intentions; Based on the aforementioned probabilistic relationships, an electric vehicle travel model is constructed; Analyze users' travel intentions and historical trajectories from the historical vehicle driving data; A Markov chain analysis is performed on the travel intentions and the historical trajectories to obtain an electric vehicle travel model.

[0009] In one embodiment, the travel intention includes average intensity, travel dispersion coefficient, and travel peak concentration where the travel rate is higher than a preset threshold; The step of analyzing the probabilistic relationship between historical trajectories and travel intentions from the historical vehicle driving data includes: Identify each functional area from the historical vehicle driving data; The statistical analysis of the historical vehicle driving data reflects the average intensity, travel dispersion coefficient, and peak travel concentration of user travel in each of the functional areas. Based on the average intensity, the travel dispersion coefficient, and the travel peak concentration, the probability of transfer between different functional areas in different time periods is evaluated. Based on the aforementioned transition probabilities, the probabilistic relationship between the historical trajectories and travel intentions of each functional area at different time periods is determined.

[0010] In one embodiment, the step of predicting the travel trajectory of a vehicle in the predicted scenario based on a preset electric vehicle travel model includes: Perform weather analysis on the predicted scenario to obtain the date, location, and weather data of the predicted scenario; The date, location, and weather data are input into a preset electric vehicle travel model to obtain the vehicle's travel trajectory in the predicted scenario. The electric vehicle travel model predicts the vehicle's travel trajectory based on the travel intention determined by the date, location, and weather data.

[0011] In one embodiment, the driving behavior further includes the user's driving habits, and the step of predicting the charge / discharge power boundaries at different time periods based on the driving behavior and the battery characteristic parameters of the user's vehicle includes: Predict vehicle energy consumption at different times based on travel trajectories in the aforementioned driving behavior; Based on the battery characteristics parameters of the user's vehicle and the user's driving habits, predict the auxiliary energy consumption of the user during driving at different times; Based on the energy consumption of travel and the energy consumption of auxiliary services, the charging and discharging power boundaries are predicted at different time periods.

[0012] In one embodiment, the step of predicting the charging and discharging power boundaries at different time periods based on the travel energy consumption and the auxiliary energy consumption includes: Based on the travel energy consumption and the auxiliary energy consumption, the theoretical charging time and theoretical charging location of the vehicle in the travel trajectory are predicted; Based on current charging prices, battery depreciation losses, and charging convenience, the process of users choosing charging time and location is simulated to obtain charging decisions; Based on the charging decision, the theoretical charging time period and the theoretical charging location are modified to obtain the charging and discharging power boundaries at different time periods.

[0013] In one embodiment, before the step of aggregating the charging and discharging power boundaries of all vehicles within the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario, the method includes: Based on the attractiveness of each functional area at different times, the attractiveness parameters of each functional area at different times are determined; The step of aggregating the charging and discharging power boundaries of all vehicles within the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario further includes: Based on the attraction parameter, the charging and discharging power boundaries of all vehicles in the same time period and functional area are aggregated to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

[0014] Furthermore, to achieve the above objectives, this application also proposes a charging and discharging resource prediction device based on user travel characteristics, the charging and discharging resource prediction device based on user travel characteristics comprising: The acquisition module is used to acquire the predicted scene and a dynamic map of the predicted scene, the dynamic map including multiple functional areas; The processing module is used to obtain the user's driving behavior in the predicted scenario based on the preset electric vehicle travel model and the dynamic map. The prediction module is used to predict the charging and discharging power boundaries at different time periods based on the driving behavior and the battery characteristic parameters of the user's vehicle. The aggregation module is used to aggregate the charging and discharging power boundaries of all vehicles in the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

[0015] Furthermore, to achieve the above objectives, this application also proposes a charging and discharging resource prediction device based on user travel characteristics. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the charging and discharging resource prediction method based on user travel characteristics as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: By introducing a dynamic map containing multiple functional zones when predicting electric vehicle charging and discharging resources, and combining it with a pre-set electric vehicle travel model to generate user driving behavior in specific predicted scenarios, this method obtains charging and discharging power boundaries for different time periods based on this driving behavior and the vehicle's own battery characteristic parameters. Finally, it aggregates the power boundaries of all vehicles within the same time period and functional zone to obtain the spatiotemporal distribution of charging and discharging resources. In other words, by using functional zones in the dynamic map as spatial constraints for travel behavior generation, driving paths, dwell times, and start-stop patterns can more closely resemble real traffic scenarios. Simultaneously, by combining battery characteristic parameters to impose physical feasible domain constraints on the power boundaries, the predicted charging and discharging demand of individual vehicles reflects both user travel intentions and the actual operating capacity of the vehicles. Aggregating power boundaries by functional zone and time period improves the spatial resolution and temporal dynamic responsiveness of the prediction results, and enhances the accuracy of characterizing the dispatchable potential of regional-level charging and discharging resources. This provides more reliable and refined data support for grid-side load regulation, charging facility planning, and vehicle-grid interaction strategy formulation, reducing prediction biases for electric vehicle charging and discharging resources and improving the accuracy of testing the spatiotemporal distribution of electric vehicle charging and discharging resources. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] 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, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the charging and discharging resource prediction method based on user travel characteristics provided in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the charging and discharging resource prediction method based on user travel characteristics provided in this application; Figure 3 This is a flowchart illustrating Embodiment 3 of the charging and discharging resource prediction method based on user travel characteristics provided in this application; Figure 4 This is a schematic diagram of the module structure of the charging and discharging resource prediction device based on user travel characteristics according to an embodiment of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the charging and discharging resource prediction method based on user travel characteristics in the embodiments of this application.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or power resource management device capable of performing the above functions. The following description uses a power resource management device as an example to illustrate this embodiment and the subsequent embodiments.

[0024] Based on this, embodiments of this application provide a method for predicting charging and discharging resources based on user travel characteristics, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the charging and discharging resource prediction method based on user travel characteristics in this application.

[0025] In this embodiment, the charging and discharging resource prediction method based on user travel characteristics includes steps S10~S40: Step S10: Obtain the predicted scene and a dynamic map of the predicted scene, wherein the dynamic map includes multiple functional areas; It should be noted that the predicted scenario refers to the specific spatiotemporal range within which charging and discharging resources are to be predicted, including specific geographical areas, time windows (such as the next 24 hours or a specific workday), and external environmental conditions (such as weather and / or holiday types). A dynamic map is a multi-dimensional map data structure constructed by overlaying semantic information that changes over time onto a basic electronic map. Functional zones are geographical units in a dynamic map that share similar travel attraction / generation characteristics, divided according to land use, user activity patterns, and traffic features; examples include residential areas, work areas, and commercial areas.

[0026] It is understandable that by acquiring dynamic maps containing multiple functional areas, complex geospatial information can be structured and semanticized, enabling travel behavior modeling to be analyzed based on functional units with clear socio-economic attributes (such as residential, commercial, and industrial).

[0027] Understandably, since functional zones are the basic source of attraction and generation for user travel activities, dividing dynamic maps into functional zones can enable power resource management equipment to accurately identify vehicle aggregation patterns and charging and discharging demand characteristics in different areas at different times, thereby providing a data foundation for building high-precision spatiotemporal prediction models.

[0028] Understandably, dynamic maps can also update the attributes of functional areas over time (such as weekdays / weekends) or external events (such as large events), adapting to changes in the real-world scene and thus improving the timeliness of prediction results.

[0029] In practical implementation, the functional area division of the dynamic map can also support the dynamic fusion of multi-source data, including mobile phone signaling data, subway card swiping records, and customer flow from Wi-Fi probes in business districts. Emerging hot spots are identified in real time through clustering algorithms and automatically marked as temporary functional areas to improve the map's response speed to sudden events (such as concerts and exhibitions).

[0030] Step S20: Based on the preset electric vehicle travel model and the dynamic map, obtain the user's driving behavior in the predicted scenario; It should be noted that the electric vehicle travel model is a probabilistic behavioral model based on Markov chains or deep sequence models, used to simulate the user's travel decision-making process in a given scenario. Driving behavior is a comprehensive travel characteristic exhibited by the user in the predicted scenario, including: the vehicle's travel trajectory, the user's travel intention, and driving habits. The travel trajectory is the vehicle's movement path in the spatiotemporal dimension. Travel intention is the user's subjective tendency to depart from or travel to a certain functional area during a specific time period, which can be quantified as a probability or intensity value. Driving habits are an individual's personalized operating patterns in acceleration and deceleration, air conditioning use, and entertainment system activation, affecting auxiliary energy consumption.

[0031] Understandably, by combining a pre-defined electric vehicle travel model with a dynamic map, it is possible to simulate the real-world behavior of vehicles in specific scenarios, starting from the individual user's travel decision-making mechanism.

[0032] Understandably, because the modeling approach based on behavioral mechanisms can effectively capture sudden changes in travel patterns caused by factors such as weather, road conditions, and holidays, it can avoid prediction bias caused by simply extrapolating historical data, thus providing a reliable behavioral basis for accurately calculating energy consumption and charging / discharging needs.

[0033] In its implementation, the electric vehicle travel model can be constructed based on the anonymized driving trajectories of 100,000 registered electric vehicles in a certain area over the past three months. A first-order Markov chain can be used to model the transition probabilities between functional areas. The inputs to the electric vehicle travel model can include the current date type (weekday / holiday), weather conditions (sunny / rainy / snowy), and real-time attractiveness scores of each functional area. The output can be the most likely travel trajectory sequence for each vehicle in the next 24 hours and its corresponding travel intention intensity value.

[0034] In practical implementation, the electric vehicle travel model can also integrate a deep reinforcement learning module to receive feedback signals from power resource management equipment (such as actual call success rate and user default rate) after each prediction, and update the reward function in the Markov transition probability accordingly, so that the electric vehicle travel model has online adaptive optimization capabilities.

[0035] Step S30: Based on the driving behavior and the battery characteristic parameters of the user's vehicle, predict the charging and discharging power boundaries at different time periods. It should be noted that battery characteristic parameters are key physical and electrochemical parameters describing the performance of electric vehicle power batteries, including battery discharge rate, battery temperature, discharge efficiency, charge / discharge cycles, and remaining capacity. The charge / discharge power boundaries are the upper limit of the maximum dispatchable charging power and the lower limit of the maximum dispatchable discharging power that a single electric vehicle can provide within a specific time period, considering factors such as remaining capacity, travel arrangements, user preferences, and grid constraints.

[0036] Understandably, by coupling refined driving behavior with individual vehicle battery characteristic parameters, it is possible to accurately assess the actual energy state and dispatchable potential of each electric vehicle at any given time.

[0037] Understandably, by introducing a user charging decision model (which comprehensively considers factors such as electricity prices, convenience, and battery depreciation), the theoretical charging and discharging demand has been modified in a more human-centered way. This makes the predicted charging and discharging power boundary no longer an idealized physical limit, but rather a range of executable scheduling commands that closely approximates the choices made by real users. Step S40: Aggregate the charging and discharging power boundaries of all vehicles within the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

[0038] It should be noted that the spatiotemporal distribution of charging and discharging resources is a two-dimensional distribution matrix of the charging and discharging power capabilities that all electric vehicles can aggregate to provide, both spatially (by functional area) and temporally (by time period), within the geographical area and time range covered by the predicted scenario. This spatiotemporal distribution can be used for grid scheduling, charging station planning, or demand response strategy formulation.

[0039] It is understandable that by aggregating the charging and discharging power boundaries of all vehicles in the same spatiotemporal unit (i.e., the same time period and the same functional area), the dispersed individual vehicle resources can be transformed into a clear, intuitive, and operationally instructive spatiotemporal distribution map of charging and discharging resources.

[0040] Understandably, using functional zones as aggregation units can integrate existing systems such as urban planning and distribution network zoning management, so as to seamlessly embed the forecast results into actual business processes. This can effectively support key application scenarios such as orderly charging guidance, distribution network expansion planning, and demand response project design, ultimately improving grid stability, optimizing infrastructure investment, and reducing users' energy costs.

[0041] In practice, the prediction process of charging and discharging power boundaries can be coupled with the real-time operating status of the distribution network. If the load rate of a certain functional area exceeds a certain threshold, the charging convenience score of that area will be automatically reduced in the user charging decision simulation, thereby guiding some vehicles to delay charging or move to nearby low-load areas, thus realizing active load regulation in coordination between vehicles and the network.

[0042] In practical implementation, since different types of batteries have different discharge depth limits and temperature rise characteristics, the aggregation step can also be extended to support the aggregation of heterogeneous electric vehicle models. For example, vehicles equipped with lithium iron phosphate batteries and ternary lithium battery vehicles can be aggregated separately, thereby providing differentiated scheduling strategies for the power grid.

[0043] Optionally, before step S40, the charging and discharging resource prediction method based on user travel characteristics further includes: Based on the attractiveness of each functional area at different times, the attractiveness parameters of each functional area at different times are determined.

[0044] It should be noted that a time period is a time unit divided into predicted time windows according to a preset granularity, used to characterize the time discretization features of user travel and charging / discharging behavior. Attractiveness is the comprehensive ability of a functional area to induce electric vehicle users to stop, charge, or discharge within a specific time period. Attractiveness is influenced by various factors, including but not limited to: pedestrian traffic, commercial activity, parking convenience, charging facility density, weather conditions, special events, and historical vehicle inflow rates. The attractiveness parameter is a dimensionless numerical value or vector used to quantify the level of attractiveness of a functional area within a specific time period.

[0045] The preset granularity can be adaptively adjusted according to emergencies. For example, during major events (such as marathons and concerts), the preset granularity can be switched to a minute-level update mode, that is, by integrating emerging signals such as social media hotspots and ticket sales data, it can quickly respond to sudden changes in crowd flow.

[0046] Understandably, by quantifying the attractiveness of each functional area at different times based on multi-source data and generating corresponding attractiveness parameters, the time-varying characteristics of urban spatial vitality can be dynamically captured. Using this attractiveness parameter as a key weighting factor can also effectively improve the realism of user travel destination selection simulation and avoid prediction bias caused by treating all functional areas equally.

[0047] In practical implementation, the attraction parameter can also be linked with the grid-side signal; that is, when the distribution transformer load rate in a certain area exceeds the threshold, the attraction parameter of that functional area is automatically reduced, thereby weakening its priority as a destination in the travel model and realizing proactive load guidance.

[0048] Optionally, step S40 may also be: Based on the attraction parameter, the charging and discharging power boundaries of all vehicles in the same time period and functional area are aggregated to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

[0049] Understandably, by introducing an attraction parameter to weight and aggregate the vehicle charging and discharging power boundaries, the resource distribution results can fully consider the actual influence of different functional areas on user behavior during specific time periods, thereby improving the physical rationality and scheduling feasibility of the aggregation results.

[0050] This embodiment provides a method for predicting charging and discharging resources based on user travel characteristics. When predicting the charging and discharging resources of electric vehicles, a dynamic map containing multiple functional areas is introduced, and a preset electric vehicle travel model is combined to generate the user's driving behavior in a specific prediction scenario. Then, based on the driving behavior and the battery characteristic parameters of the vehicle itself, the charging and discharging power boundaries for different time periods are obtained. Finally, the power boundaries of all vehicles in the same time period and functional area are aggregated to obtain the spatiotemporal distribution of charging and discharging resources. In other words, by using functional areas in the dynamic map as spatial constraints for travel behavior generation, driving routes, dwell times, and start-stop patterns can more closely resemble real traffic scenarios. Simultaneously, by combining battery characteristic parameters to impose physical feasible domain constraints on the power boundary, the predicted charging and discharging demand of individual vehicles reflects both user travel intentions and the actual operating capacity of the vehicles. Furthermore, by aggregating power boundaries by functional area and time period, the spatial resolution and temporal dynamic responsiveness of the prediction results are improved. This also enhances the accuracy of characterizing the dispatchable potential of regional-level charging and discharging resources. Consequently, this provides more reliable and refined data support for grid-side load regulation, charging facility planning, and vehicle-grid interaction strategy formulation, reducing prediction biases for electric vehicle charging and discharging resources and improving the accuracy of spatiotemporal distribution testing of electric vehicle charging and discharging resources.

[0051] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Step S20 also includes steps S01 to S03: Step S01: Based on a preset electric vehicle travel model, predict the travel trajectory of the vehicle in the predicted scenario; Step S02: Based on the dynamic map, perform congestion analysis for each travel period to obtain the degree of impact of road conditions on user travel; Step S03: Correct the travel trajectory based on the degree of impact to obtain the user's driving behavior in the predicted scenario.

[0052] It should be noted that the degree of impact refers to the intensity of disruption that current or predicted traffic congestion will cause to users' original travel plans.

[0053] Understandably, by first generating an initial travel trajectory based on a preset model, then combining it with real-time congestion analysis from a dynamic map to obtain the degree of road condition impact, and then correcting the trajectory accordingly, the final driving behavior can not only reflect the user's regular travel patterns, but also dynamically respond to changes in the external traffic environment, thereby improving the accuracy of behavior prediction.

[0054] In practical implementation, to determine the degree of impact of road conditions on users' travel, a sentiment analysis module can be introduced. With the user's consent, comments from social media or navigation software can be crawled to extract the intensity of public sentiment as an auxiliary indicator, thereby improving the sensitivity to the impact of sudden congestion.

[0055] Furthermore, prior to step S01, the charging and discharging resource prediction method based on user travel characteristics further includes: Obtain historical vehicle driving data; Analyze the probabilistic relationship between each historical vehicle driving data and travel intentions; Based on the aforementioned probabilistic relationships, an electric vehicle travel model is constructed; Analyze users' travel intentions and historical trajectories from the historical vehicle driving data; A Markov chain analysis is performed on the travel intentions and the historical trajectories to obtain an electric vehicle travel model.

[0056] It should be noted that historical vehicle driving data refers to the pre-collected and stored operation records of electric vehicles. Historical trajectories are continuous position sequences formed by vehicles in the spatiotemporal dimension during a single or multiple trips. The probabilistic relationship is the statistical dependence between historical trajectories and travel intentions. Travel intentions include average intensity, travel dispersion coefficient, and the concentration of peak travel periods where the travel rate exceeds a preset threshold.

[0057] It should be noted that Markov chain analysis models the user's movement between functional zones as a Markov process, meaning that the functional zone at the next moment depends only on the current functional zone and is independent of earlier history. By statistically analyzing the frequency of functional zone transitions in historical trajectories, a state transition probability matrix is ​​constructed, thereby formally expressing the trajectory evolution patterns driven by travel intentions.

[0058] Understandably, by mining the probabilistic relationship between historical vehicle driving data and travel intentions, and building an electric vehicle travel model based on this probabilistic relationship, the model can delve into the intrinsic motivations of users' travel decisions, thereby improving the model's interpretability and generalization ability.

[0059] Understandably, using Markov chains to formally model travel intentions and historical trajectories can abstract complex individual behaviors into computable state transition processes, ensuring both the simplicity and efficiency of the model and preserving key behavioral temporal dependencies.

[0060] Understandably, by explicitly modeling travel intentions as latent variables and coupling them with trajectories, the model can effectively distinguish the different motivations behind the same path, thereby more accurately judging users' tolerance and preferences for charging time and location in charging and discharging prediction.

[0061] Furthermore, the step of analyzing the probabilistic relationship between historical trajectories and travel intentions from the historical vehicle driving data further includes: Identify each functional area from the historical vehicle driving data; The statistical analysis of the historical vehicle driving data reflects the average intensity, travel dispersion coefficient, and peak travel concentration of user travel in each of the functional areas. Based on the average intensity, the travel dispersion coefficient, and the travel peak concentration, the probability of transfer between different functional areas in different time periods is evaluated. Based on the aforementioned transition probabilities, the probabilistic relationship between the historical trajectories and travel intentions of each functional area at different time periods is determined.

[0062] It should be noted that average intensity is the average number of trips or vehicles attracted to a functional area per unit time within a specific period, used to characterize the daily activity level of that area. The trip dispersion coefficient is a quantitative indicator of the dispersion of user travel time or destination choices. Peak travel concentration is the proportion of trips occurring during a preset peak period to the total daily trip volume, used to measure the degree of concentration of travel demand over time. Transfer probability is the probability that, given a user is currently located in a functional area and within a specific time period, their next destination will be another functional area.

[0063] It is understandable that since high concentration and low dispersion can clearly indicate rigid commuting demand, while high dispersion implies flexible travel, a comprehensive evaluation of the transfer probability between functional areas based on three dimensions—average intensity, travel dispersion coefficient, and peak travel concentration—can reflect the underlying regularity and motivational differences in travel behavior, thereby improving the physical rationality and predictive accuracy of the transfer probability.

[0064] In practical implementation, the travel dispersion coefficient can also be the spatiotemporal joint dispersion, which measures the entropy of temporal dispersion and destination spatial distribution, thereby distinguishing between two types of users: those with regular time but random location and those with fixed location but flexible time.

[0065] Furthermore, step S10 also includes: Perform weather analysis on the predicted scenario to obtain the date, location, and weather data of the predicted scenario; The date, location, and weather data are input into a preset electric vehicle travel model to obtain the vehicle's travel trajectory in the predicted scenario. The electric vehicle travel model predicts the vehicle's travel trajectory based on the travel intention determined by the date, location, and weather data.

[0066] It should be noted that weather analysis is the process of acquiring and analyzing meteorological elements within the time and space range covered by the forecast scenario by calling meteorological service interfaces or local meteorological databases, and outputting structured weather data.

[0067] Understandably, by analyzing the weather in the predicted scenario and obtaining date, location and weather data, external environmental disturbances can be incorporated into the travel behavior modeling process. Through the model's internal mechanism, these external environmental disturbances can be transformed into dynamic travel intentions. Based on these intentions, trajectories can be predicted, thus realizing causal chain modeling from environmental perception to behavioral response, thereby improving the realism of trajectory prediction.

[0068] Based on the first and second embodiments of this application, the same or similar content as the above embodiments in the third embodiment of this application can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to...Figure 3 Step S30 also includes steps S1 to S3: Step S1: Predict the vehicle's travel energy consumption at different times based on the travel trajectory in the driving behavior; Step S2: Based on the battery characteristic parameters of the user's vehicle and the user's driving habits, predict the auxiliary energy consumption of the user during driving at different times. Step S3: Based on the travel energy consumption and the auxiliary energy consumption, predict the charging and discharging power boundaries at different time periods.

[0069] It should be noted that travel energy consumption refers to the electrical energy consumed by a vehicle during operation to overcome rolling resistance, air resistance, gradient resistance, and acceleration inertia. Auxiliary energy consumption refers to the electrical energy consumed by onboard equipment other than the drive system during vehicle operation or parking, mainly including air conditioning, seat heating, infotainment systems, and lighting.

[0070] Understandably, using driving habits as a key input for energy consumption analysis can differentiate energy consumption among different users of the same vehicle model, thereby providing data support for differentiated pricing and personalized guidance strategies, and enhancing user acceptance.

[0071] Understandably, by accurately predicting travel energy consumption based on travel trajectories and combining individual user battery characteristics and driving habits to predict auxiliary energy consumption, the total energy consumption of the vehicle can be assessed in a personalized and scenario-based manner, thereby improving the accuracy of energy state prediction.

[0072] Furthermore, step S3 also includes: Based on the travel energy consumption and the auxiliary energy consumption, the theoretical charging time and theoretical charging location of the vehicle in the travel trajectory are predicted; Based on current charging prices, battery depreciation losses, and charging convenience, the process of users choosing charging time and location is simulated to obtain charging decisions; Based on the charging decision, the theoretical charging time period and the theoretical charging location are modified to obtain the charging and discharging power boundaries at different time periods.

[0073] It should be noted that the theoretical charging period is calculated solely based on energy balance constraints and travel arrangements, representing the necessary or optional charging window for vehicles within the travel trajectory. It does not consider user subjective intentions or external economic factors. The theoretical charging location refers to functional areas or stations along the travel route or near the destination that meet physical accessibility requirements and have charging facilities. The charging price is the unit electricity price payable for using charging services at a specific time and location. Battery depreciation loss is the cost of lifespan loss caused by accelerated battery aging due to charging. Charging convenience is a user's comprehensive perception and evaluation of a charging location in terms of time, space, and experience. The charging decision is the user's final choice regarding whether to charge, when to charge, and where to charge, after comprehensively weighing charging price, battery depreciation loss, and charging convenience.

[0074] Understandably, the theoretical charging time and space points are first generated based on energy consumption prediction, and then the three factors of charging price, battery depreciation loss and charging convenience are introduced to simulate the user's real decision-making process. This makes the final determined charging and discharging power boundary not an idealized physical limit, but an executable scheduling instruction that reflects the user's economic rationality and behavioral preferences, thereby improving the practical feasibility of resource prediction.

[0075] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the charging and discharging resource prediction method based on user travel characteristics in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0076] This application also provides a charging and discharging resource prediction device based on user travel characteristics. Please refer to [reference needed]. Figure 4 The charging and discharging resource prediction device based on user travel characteristics includes: The acquisition module 10 is used to acquire the predicted scene and a dynamic map of the predicted scene, the dynamic map including multiple functional areas; Processing module 20 is used to obtain the user's driving behavior in the predicted scenario based on a preset electric vehicle travel model and the dynamic map; Prediction module 30 is used to predict the charging and discharging power boundaries at different time periods based on the driving behavior and the battery characteristic parameters of the user's vehicle. The aggregation module 40 is used to aggregate the charging and discharging power boundaries of all vehicles in the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

[0077] Optionally, the processing module 20 is further configured to predict the travel trajectory of vehicles in the predicted scenario based on a preset electric vehicle travel model; perform congestion analysis on each travel period based on the dynamic map to obtain the degree of influence of road conditions on user travel; and correct the travel trajectory based on the degree of influence to obtain the user's driving behavior in the predicted scenario, wherein the driving behavior includes the travel trajectory and the user's travel intention; and the travel intention includes average intensity, travel dispersion coefficient, and travel peak concentration where the travel rate is higher than a preset threshold.

[0078] Optionally, the processing module 20 is also used to acquire historical vehicle driving data; The probabilistic relationship between historical trajectories and travel intentions is analyzed from the historical vehicle driving data; an electric vehicle travel model is constructed based on the probabilistic relationship; the user's travel intentions and historical trajectories are analyzed from the historical vehicle driving data; Markov chain analysis is performed on the travel intentions and historical trajectories to obtain the electric vehicle travel model.

[0079] Optionally, the processing module 20 is further configured to identify each functional area from the historical vehicle driving data; statistically analyze the average intensity, travel dispersion coefficient, and peak travel concentration of user travel volume in each functional area reflected in the historical vehicle driving data; evaluate the transfer probability between each functional area at different time periods based on the average intensity, the travel dispersion coefficient, and the peak travel concentration; and determine the probabilistic relationship between the historical trajectories and travel intentions of each functional area at different time periods based on the transfer probability.

[0080] Optionally, the processing module 20 is further configured to perform weather analysis on the predicted scenario to obtain the date, location, and weather data of the predicted scenario; input the date, location, and weather data into a preset electric vehicle travel model to obtain the travel trajectory of the vehicle in the predicted scenario; the electric vehicle travel model predicts the travel trajectory of the vehicle based on the travel intention determined by the date, location, and weather data.

[0081] Optionally, the driving behavior also includes the user's driving habits; The prediction module 30 is also used to predict the energy consumption of the vehicle during different time periods based on the travel trajectory in the driving behavior; predict the auxiliary energy consumption of the user during driving at different time periods based on the battery characteristic parameters of the user's vehicle and the driving habits; and predict the charging and discharging power boundaries at different time periods based on the travel energy consumption and the auxiliary energy consumption.

[0082] Optionally, the prediction module 30 is further configured to predict the theoretical charging time period and theoretical charging location of the vehicle in the travel trajectory based on the travel energy consumption and the auxiliary energy consumption; simulate the process of the user selecting the charging time period and charging location based on the current charging price, battery depreciation loss and charging convenience to obtain a charging decision; and modify the theoretical charging time period and the theoretical charging location based on the charging decision to obtain the charging and discharging power boundaries at different time periods.

[0083] Optionally, the aggregation module 40 is further configured to determine the attraction parameters of each functional area in different time periods based on the attraction of each functional area in different time periods; and based on the attraction parameters, aggregate the charging and discharging power boundaries of all vehicles in the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

[0084] The charging and discharging resource prediction device based on user travel characteristics provided in this application adopts the charging and discharging resource prediction method based on user travel characteristics in the above embodiments. It can solve the technical problem that the current prediction method does not combine dynamic maps and the characteristics of electric vehicles, thus causing the prediction results to be biased. Compared with the prior art, the beneficial effects of the charging and discharging resource prediction device based on user travel characteristics provided in this application are the same as the beneficial effects of the charging and discharging resource prediction method based on user travel characteristics provided in the above embodiments. Moreover, the other technical features of the charging and discharging resource prediction device based on user travel characteristics are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0085] This application provides a charging and discharging resource prediction device based on user travel characteristics. The charging and discharging resource prediction device based on user travel characteristics includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the charging and discharging resource prediction method based on user travel characteristics in the above embodiment 1.

[0086] The following is for reference. Figure 5This document illustrates a structural schematic diagram of a charging and discharging resource prediction device based on user travel characteristics, suitable for implementing embodiments of this application. The charging and discharging resource prediction device based on user travel characteristics in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The charging and discharging resource prediction device based on user travel characteristics shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0087] like Figure 5 As shown, the charging and discharging resource prediction device based on user travel characteristics may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the charging and discharging resource prediction device based on user travel characteristics. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the charge / discharge resource prediction device based on user travel characteristics to exchange data wirelessly or via wired communication with other devices. Although a charge / discharge resource prediction device based on user travel characteristics with various systems is shown in the figure, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0088] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0089] The charging and discharging resource prediction device based on user travel characteristics provided in this application adopts the charging and discharging resource prediction method based on user travel characteristics in the above embodiments. It can solve the technical problem that the current prediction method does not combine dynamic maps and the characteristics of electric vehicles, thus causing the prediction results to be biased. Compared with the prior art, the beneficial effects of the charging and discharging resource prediction device based on user travel characteristics provided in this application are the same as the beneficial effects of the charging and discharging resource prediction method based on user travel characteristics provided in the above embodiments. Moreover, other technical features in the charging and discharging resource prediction device based on user travel characteristics are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0090] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0091] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0092] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the charging and discharging resource prediction method based on user travel characteristics in the above embodiments.

[0093] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0094] The aforementioned computer-readable storage medium may be included in a charge / discharge resource prediction device based on user travel characteristics; or it may exist independently and not be assembled into a charge / discharge resource prediction device based on user travel characteristics.

[0095] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the charging and discharging resource prediction device based on user travel characteristics, enable the charging and discharging resource prediction device based on user travel characteristics to implement the aforementioned charging and discharging resource prediction method based on user travel characteristics.

[0096] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0098] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0099] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described method for predicting charging and discharging resources based on user travel characteristics. This solves the technical problem that current prediction methods do not incorporate dynamic maps and the characteristics of electric vehicles, leading to deviations in prediction results. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the charging and discharging resource prediction method based on user travel characteristics provided in the above embodiments, and will not be elaborated upon here.

[0100] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for predicting charging and discharging resources based on user travel characteristics.

[0101] The computer program product provided in this application can solve the technical problem that current prediction methods do not combine dynamic maps and the characteristics of electric vehicles, resulting in biased prediction results. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the charging and discharging resource prediction method based on user travel characteristics provided in the above embodiments, and will not be repeated here.

[0102] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for predicting charging and discharging resources based on user travel characteristics, characterized in that, The method includes: Obtain the predicted scene and a dynamic map of the predicted scene, the dynamic map including multiple functional areas; Based on the preset electric vehicle travel model and the dynamic map, the user's driving behavior in the predicted scenario is obtained; Based on the driving behavior and the battery characteristic parameters of the user's vehicle, the charging and discharging power boundaries at different time periods are predicted. By aggregating the charging and discharging power boundaries of all vehicles within the same time period and functional area, the spatiotemporal distribution of charging and discharging resources in the predicted scenario is obtained.

2. The method as described in claim 1, characterized in that, The steps for obtaining user driving behavior in the predicted scenario based on the preset electric vehicle travel model and the dynamic map include: Based on a preset electric vehicle travel model, predict the travel trajectory of the vehicle in the predicted scenario; Based on the dynamic map, congestion analysis is performed for each travel period to obtain the degree of impact of road conditions on user travel. The travel trajectory is corrected based on the degree of impact to obtain the user's driving behavior in the predicted scenario. The driving behavior includes the travel trajectory and the user's travel intention.

3. The method as described in claim 2, characterized in that, Before the step of predicting the travel trajectory of vehicles in the predicted scenario based on a preset electric vehicle travel model, the following steps are included: Obtain historical vehicle driving data; Analyze the probabilistic relationship between each historical vehicle driving data and travel intentions; Based on the aforementioned probabilistic relationships, an electric vehicle travel model is constructed; Analyze users' travel intentions and historical trajectories from the historical vehicle driving data; A Markov chain analysis is performed on the travel intentions and the historical trajectories to obtain an electric vehicle travel model.

4. The method as described in claim 3, characterized in that, The travel intention includes average intensity, travel dispersion coefficient, and peak travel concentration where the travel rate is higher than a preset threshold. The step of analyzing the probabilistic relationship between historical trajectories and travel intentions from the historical vehicle driving data includes: Identify each functional area from the historical vehicle driving data; The statistical analysis of the historical vehicle driving data reflects the average intensity, travel dispersion coefficient, and peak travel concentration of user travel in each of the functional areas. Based on the average intensity, the travel dispersion coefficient, and the travel peak concentration, the probability of transfer between different functional areas in different time periods is evaluated. Based on the aforementioned transition probabilities, the probabilistic relationship between the historical trajectories and travel intentions of each functional area at different time periods is determined.

5. The method as described in claim 2, characterized in that, The step of predicting the travel trajectory of vehicles in the predicted scenario based on a preset electric vehicle travel model includes: Perform weather analysis on the predicted scenario to obtain the date, location, and weather data of the predicted scenario; The date, location, and weather data are input into a preset electric vehicle travel model to obtain the vehicle's travel trajectory in the predicted scenario. The electric vehicle travel model predicts the vehicle's travel trajectory based on the travel intention determined by the date, location, and weather data.

6. The method as described in claim 1, characterized in that, The driving behavior also includes the user's driving habits. The step of predicting the charge and discharge power boundaries at different time periods based on the driving behavior and the battery characteristic parameters of the user's vehicle includes: Predict vehicle energy consumption at different times based on travel trajectories in the aforementioned driving behavior; Based on the battery characteristics of the user's vehicle and the user's driving habits, predict the auxiliary energy consumption of the user during driving at different times; Based on the energy consumption of travel and the energy consumption of auxiliary services, the charging and discharging power boundaries are predicted at different time periods.

7. The method as described in claim 6, characterized in that, The step of predicting the charging and discharging power boundaries at different time periods based on the travel energy consumption and the auxiliary energy consumption includes: Based on the travel energy consumption and the auxiliary energy consumption, the theoretical charging time and theoretical charging location of the vehicle in the travel trajectory are predicted; Based on current charging prices, battery depreciation losses, and charging convenience, the process of users choosing charging time and location is simulated to obtain charging decisions; Based on the charging decision, the theoretical charging time period and the theoretical charging location are modified to obtain the charging and discharging power boundaries at different time periods.

8. The method as described in claim 1, characterized in that, Before the step of aggregating the charging and discharging power boundaries of all vehicles within the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario, the following steps are included: Based on the attractiveness of each functional area at different times, the attractiveness parameters of each functional area at different times are determined; The step of aggregating the charging and discharging power boundaries of all vehicles within the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario further includes: Based on the attraction parameter, the charging and discharging power boundaries of all vehicles in the same time period and functional area are aggregated to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

9. A charging and discharging resource prediction device based on user travel characteristics, characterized in that, The device includes: The acquisition module is used to acquire the predicted scene and a dynamic map of the predicted scene, the dynamic map including multiple functional areas; The processing module is used to obtain the user's driving behavior in the predicted scenario based on the preset electric vehicle travel model and the dynamic map. The prediction module is used to predict the charging and discharging power boundaries at different time periods based on the driving behavior and the battery characteristic parameters of the user's vehicle. The aggregation module is used to aggregate the charging and discharging power boundaries of all vehicles in the same time period and functional area to obtain the spatiotemporal distribution of charging and discharging resources in the predicted scenario.

10. A charging and discharging resource prediction device based on user travel characteristics, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the charging and discharging resource prediction method based on user travel characteristics as described in any one of claims 1 to 8.

Images