Site selection decision method and device for new energy vehicle energy supply and conversion facility

Abstract

The application discloses a new energy automobile energy supply and conversion facility site selection decision method and device, wherein the method comprises the following steps: acquiring traffic flow data and energy supply and conversion facility data in a planning area; dividing the planning area according to the traffic flow data and the energy supply and conversion facility data to obtain a plurality of traffic zones; establishing a nonlinear high-dimensional space-time model of the traffic flow data and the traffic zones, and obtaining a feasible decision set by using the nonlinear high-dimensional space-time model; performing dimension reduction processing on the nonlinear high-dimensional space-time model, and obtaining suitable strategy parameters in combination with a case data knowledge base; establishing a prediction model to evaluate the traffic flow state and the energy supply and conversion facility service level in the future planning area, and screening in the feasible decision set according to the evaluation result to obtain a plurality of optimal decisions; performing rank-sum ratio sorting on the plurality of optimal decisions to obtain a final decision result; and thus the operation efficiency of the regional traffic system and the energy supply and conversion infrastructure service level can be improved.

Description

Technical Field

[0001] This application relates to the fields of intelligent transportation and energy storage and utilization technology for new energy vehicles, and in particular to a site selection decision method, device, equipment and medium for energy supply and swapping facilities for new energy vehicles. Background Technology

[0002] Against the backdrop of the global promotion of new energy vehicles and smart mobility, and with the rapid development of new energy vehicles in China, urban planning areas need to build supporting energy supply and swapping infrastructure for new energy vehicles to provide good transportation services. The site selection of energy supply and swapping facilities is becoming an increasingly hot topic. The key is to determine the site selection and simultaneous service capacity of the energy supply facilities in order to meet user needs to the greatest extent possible without increasing excessive economic costs.

[0003] For example, Xiamen has significantly accelerated the construction of energy supply and swapping infrastructure in recent years, and the layout of energy supply facilities has been continuously optimized. However, it still faces various challenges. While the concentration of functional construction on the island is high, with a charging pile density of 24.5 units per square meter in the core area, the business model for energy supply and swapping is still immature. The overall scale of the new energy vehicle industry and its supporting system are mismatched. The electrification rate of dump trucks, concrete mixer trucks, and logistics vehicles is low. There is a structural scarcity of energy supply infrastructure, and the development of energy supply and swapping facilities (especially medium- and heavy-duty or dedicated charging piles) is unbalanced. Therefore, in addition to increasing the charging pile-to-vehicle ratio and expanding the construction of energy supply and swapping infrastructure, the rationalization of distribution and site selection should also be considered in conjunction with factors such as the imbalance in traffic development and the preferences of traffic users.

[0004] Based on past research and practical experience, the site selection for energy supply and swapping facilities should consider the following factors: First, ensuring the normal operation and maintenance of the infrastructure, taking into account inter-regional competition and the traffic and site conditions of specific locations; second, maximizing service to existing and potential customers while meeting the above requirements, which means determining the optimal site for the infrastructure based on consumer traffic behavior analysis and demand forecasting. Furthermore, with the development of new energy vehicles and intelligent transportation, new factors should be considered, and more flexible and scalable methods should be adopted.

[0005] With the rise of smart technologies, the decision-making process for the site selection of energy supply and swapping facilities increasingly relies on extensive data analysis and intelligent algorithms. Through intelligent algorithms and big data analysis, the usage, idle time, and demand of energy supply facilities can be monitored and analyzed in real time. This allows for the establishment of a more comprehensive remote monitoring system for electric vehicle charging piles, providing real-time data and reports. This enables charging pile operators and management departments to understand the usage of charging piles in a timely manner, effectively manage charging piles, and ensure their normal operation, thereby achieving a more scientific and intelligent site selection scheme for energy supply facilities. At the same time, artificial intelligence technology can also predict traffic congestion and optimize the distribution of energy supply and swapping facilities, realizing a comprehensive, efficient, and intelligent energy supply network.

[0006] Currently, research findings on the site selection of power supply and energy exchange facilities include data analysis methods, site selection strategy optimization, and decision evaluation indicators. These research directions also point out the main challenges facing this issue: (1) The site selection of power supply and energy exchange facilities requires a large amount of data support, including user behavior data, traffic data, and existing power supply and energy exchange facility service data. The accuracy, timeliness, and reliability of the data need to be fully considered. (2) Accurate analysis and prediction of the data is also a complex task. The decision prediction of selecting appropriate site selection strategies for power supply and energy exchange infrastructure based on the data analysis results needs to comprehensively consider multiple factors. (3) The evaluation process for the site selection of power supply and energy exchange facilities needs to be matched with the city's infrastructure construction and transportation planning to ensure that the construction of power supply and energy exchange facilities will not have an adverse impact on traffic flow and urban development. Summary of the Invention

[0007] This application aims to at least partially address one of the technical problems in the aforementioned technologies. To this end, one objective of this application is to propose a site selection decision-making method for energy supply and swapping facilities for new energy vehicles. This method uses a predictive model to forecast traffic flow patterns and the service level of energy supply and swapping facilities within a region of interest over a future period as evaluation indicators to obtain an optimal site selection strategy. This solves the optimization problem of matching energy supply and swapping facilities with changes in traffic flow patterns, thereby improving the operational efficiency of the regional transportation system and the service level of energy supply and swapping infrastructure.

[0008] To achieve the above objectives, the first aspect of this application proposes a site selection method for energy supply and swapping facilities for new energy vehicles, comprising the following steps:

[0009] The process involves: acquiring traffic flow data and energy exchange facility data within the planning area; dividing the planning area into multiple traffic zones based on the traffic flow data and energy exchange facility data; establishing a nonlinear high-dimensional spatiotemporal model of the traffic flow data and the traffic zones using fuzzy control theory, and obtaining a feasible decision set for potential energy exchange facility construction sites using the nonlinear high-dimensional spatiotemporal model; performing dimensionality reduction on the nonlinear high-dimensional spatiotemporal model and combining it with a case data knowledge base to obtain appropriate strategy parameters; establishing a prediction model to evaluate the future traffic flow status and energy exchange facility service level within the planning area, and using an optimization algorithm to filter the feasible decision set based on the evaluation results and the strategy parameters to obtain multiple optimal decisions; and ranking the multiple optimal decisions by rank-sum ratio to obtain the final decision result.

[0010] Based on the aforementioned technical means, this embodiment first acquires traffic flow data and energy exchange facility data within the planning area; then, it divides the planning area into multiple traffic zones based on the traffic flow data and energy exchange facility data; next, it uses fuzzy control theory to establish a nonlinear high-dimensional spatiotemporal model of the traffic flow data and traffic zones, and uses this nonlinear high-dimensional spatiotemporal model to obtain a feasible decision set for potential energy exchange facility construction points; then, it performs dimensionality reduction processing on the nonlinear high-dimensional spatiotemporal model and combines it with a case data knowledge base to obtain appropriate strategy parameters; finally, it establishes a prediction model for the future planning area... Traffic flow conditions and the service level of energy supply and exchange facilities are assessed. Based on the assessment results and strategy parameters, an optimization algorithm is used to filter from the feasible decision set to obtain multiple optimal decisions. Finally, the multiple optimal decisions are ranked by rank-sum ratio to obtain the final decision result. Thus, by establishing a predictive model to predict the traffic flow conditions and the service level of energy supply and exchange facilities in the area of ​​interest over a future period as evaluation indicators, the optimal location strategy is obtained, solving the optimization problem of matching energy supply and exchange facilities with changes in traffic flow conditions. This can improve the operational efficiency of the regional transportation system and the service level of energy supply and exchange infrastructure.

[0011] In addition, the site selection decision method for energy supply and swapping facilities for new energy vehicles proposed in the above embodiments of this application may also have the following additional technical features:

[0012] Furthermore, it also includes: obtaining the corresponding energy supply and exchange facility construction points based on the final decision results, and storing the corresponding traffic flow data and energy supply and exchange facility data in the case data knowledge base after construction is carried out at the construction points.

[0013] Furthermore, the nonlinear high-dimensional spatiotemporal model is subjected to dimensionality reduction processing, and suitable strategy parameters are obtained by combining the case data knowledge base. This includes: using fuzzy control technology to reduce the dimensionality of the nonlinear high-dimensional spatiotemporal model; comparing the historical case data models stored in the case data knowledge base with the nonlinear high-dimensional spatiotemporal model to filter out similar cases; and obtaining suitable strategy parameters based on the similar cases.

[0014] Furthermore, the rank-sum ratios of the multiple optimal decisions are ranked, including: calculating the rank-sum ratios of the multiple optimal decisions from smallest to largest based on the benefit indicators; obtaining the dimensionless statistic RSR value through rank transformation; and ranking the multiple optimal decisions based on the RSR value, wherein a higher RSR value corresponds to a better performance in terms of cost, and a lower RSR value corresponds to a worse performance in terms of cost.

[0015] A second aspect of this application provides a site selection decision-making device for energy supply and swapping facilities for new energy vehicles, comprising: a data acquisition module for acquiring traffic flow data and energy supply and swapping facility data within a planning area; a partitioning module for partitioning the planning area according to the traffic flow data and energy supply and swapping facility data to obtain multiple traffic zones; a generation module for establishing a nonlinear high-dimensional spatiotemporal model of the traffic flow data and the traffic zones using fuzzy control theory, and using the nonlinear high-dimensional spatiotemporal model to obtain a set of feasible decisions for potential energy supply and swapping facility construction sites; a processing module for performing dimensionality reduction processing on the nonlinear high-dimensional spatiotemporal model and obtaining appropriate strategy parameters by combining case data knowledge base; and an optimized site selection module for establishing a prediction model to evaluate the traffic flow status and service level of energy supply and swapping facilities within the future planning area, and using an optimization algorithm to filter the feasible decision set according to the evaluation results and the strategy parameters to obtain multiple optimal decisions; and sorting the multiple optimal decisions by rank-sum ratio to obtain the final decision result.

[0016] Furthermore, it also includes an update module, which is used to obtain the corresponding energy supply and exchange facility construction points based on the final decision result, and after construction is carried out at the construction points, store the corresponding traffic flow data and energy supply and exchange facility data into the case data knowledge base.

[0017] Furthermore, the processing module is also used to: perform dimensionality reduction processing on the nonlinear high-dimensional spatiotemporal model using fuzzy control technology; compare the historical case data model stored in the case data knowledge base with the nonlinear high-dimensional spatiotemporal model to filter out similar cases; and obtain appropriate strategy parameters based on the similar cases.

[0018] Furthermore, the site selection optimization module is also used to: calculate the rank-sum ratio of multiple optimal decisions based on the benefit indicators from smallest to largest; obtain the dimensionless statistic RSR (Rank-sum ratio) value through rank transformation, and rank multiple optimal decisions based on the RSR value. The higher the RSR value, the better the decision performs in terms of cost, and the lower the RSR value, the worse the decision performs in terms of cost.

[0019] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the site selection decision method for energy swapping facilities for new energy vehicles as described in the above embodiments.

[0020] A fourth aspect of this application provides a computer-readable storage medium storing computer instructions for causing the computer to execute the site selection decision method for energy swapping facilities for new energy vehicles as described in the above embodiments.

[0021] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating the site selection decision-making method for energy supply and swapping facilities for new energy vehicles according to an embodiment of this application.

[0023] Figure 2 This is a framework diagram of an optimized model according to an embodiment of this application;

[0024] Figure 3 This is a schematic diagram of traffic zone division according to an embodiment of this application.

[0025] Figure 4 This is a knowledge graph semantic association graph of the multi-objective fitness function descriptor according to an embodiment of this application;

[0026] Figure 5 This is a block diagram of a site selection decision device for energy supply and swapping facilities for new energy vehicles according to an embodiment of this application;

[0027] Figure 6 This is an example diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0028] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0029] To better understand the above technical solutions, exemplary embodiments of this application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0030] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0031] Please see Figure 1 , Figure 1 This is a flowchart illustrating the site selection decision method for energy supply and swapping facilities for new energy vehicles according to an embodiment of this application. Figure 1 As shown, the site selection decision-making method for the energy supply and swapping facilities of new energy vehicles includes the following steps:

[0032] S101, acquire traffic flow data and energy supply and conversion facility data within the planning area.

[0033] As an example, traffic flow data and energy supply and swapping facility data include origin-destination travel demand data, traffic flow density data, urban planning layout data, service status data of energy supply and swapping facilities, and idle status data of new energy vehicles. Among them, the service status data of energy supply and swapping facilities includes the layout, quantity, and usage frequency data of energy supply and swapping facilities; the idle status data of new energy vehicles includes vehicle type, battery type, and reported information on parking location and reserved parking duration in the idle state.

[0034] It should be noted that the above data may specifically include vehicle speed, vehicle density, parking time, number of vehicles reporting charging and energy swapping needs, energy supply duration, number of energy supply and energy swapping facilities, etc., but this application does not make specific limitations on these.

[0035] S102 divides the planning area into multiple traffic zones based on traffic flow data and energy supply and exchange facility data.

[0036] As an example, based on the planning constraints in the actual urban scenario, constraints are set for the energy supply and exchange facility deployment optimization model. Combined with the urban planning layout data mentioned above, traffic zones are divided into planning areas. The planning constraints in the actual urban scenario can be described and generated through the optimization constraint configuration file or data packet format designed in this application. The file or data packet is read by a preset interface to import the constraints.

[0037] Specifically, when dividing the planning area into traffic zones, based on the aforementioned urban planning layout data and planning restrictions, and combined with past planning decision parameters, the planning area is divided into traffic zones using spectral clustering based on traffic volume. This results in multiple traffic zones with stable spectral characteristics, as shown in the specific division results. Figure 3 As shown.

[0038] S103 uses fuzzy control theory to establish a nonlinear high-dimensional spatiotemporal model of traffic flow data and traffic zones, and uses the nonlinear high-dimensional spatiotemporal model to obtain a feasible decision set of potential energy supply and exchange facility construction sites.

[0039] In other words, traffic OD travel demand data, traffic flow density data, and vehicle idle status data are semantically associated with the divided traffic zones using a knowledge graph, and mapped to a nonlinear high-dimensional spatiotemporal model within the planning area; based on the mapped nonlinear high-dimensional spatiotemporal model, a set of potential energy supply and exchange infrastructure construction and optimization points is obtained, that is, the coordinate set of feasible solutions for site selection.

[0040] As an example, a graph structure representation is introduced during mapping. Traffic zones are set as vertices of the graph, the existence of traffic paths between zones is set as edges, and the traffic busyness between zones is set as a dynamic weight, which is determined by historical traffic flow data. Considering the tidal characteristics of traffic flow, the data is adjusted based on traffic flow data of the same or different road segments at different times such as year, quarter, month, week, and day. Then, based on the nonlinear high-dimensional spatiotemporal model, potential optimal construction points for power supply and exchange facilities are obtained based on the principle of truncated Gaussian distribution, thereby obtaining the Pareto marginal optimization feasible solution set for the site selection multi-objective optimization problem.

[0041] S104 performs dimensionality reduction on the nonlinear high-dimensional spatiotemporal model and obtains appropriate policy parameters by combining the case data knowledge base.

[0042] In other words, based on the embedded physical dynamics laws, causal knowledge, and logical knowledge, fuzzy reinforcement learning and chaotic phase space reconstruction techniques are used to transform nonlinear high-dimensional spatiotemporal problems into low-dimensional state spaces, capturing the nonlinear dynamic behavior in regional traffic systems. Relevant parameters are obtained from the case data knowledge base and output to the next step. Specifically, fuzzy control theory (such as fuzzy reinforcement learning and chaos theory) is used to solve nonlinear and spatiotemporally high-dimensional problems in traffic systems. Real-time traffic flow data, traffic statistics data at different time periods, and vehicle idle state data are used as input vectors. Successful cases are extracted from the case data knowledge base, and appropriate strategy parameters are automatically selected and output to the next step in combination with real-time traffic statistics data and energy supply and exchange facility service data.

[0043] As an example, the nonlinear high-dimensional spatiotemporal model is dimensionality reduced, and suitable policy parameters are obtained by combining the case data knowledge base. This includes: using fuzzy control technology to reduce the dimensionality of the nonlinear high-dimensional spatiotemporal model; comparing the historical case data models stored in the case data knowledge base with the nonlinear high-dimensional spatiotemporal model to select similar cases; and obtaining suitable policy parameters based on the similar cases.

[0044] It should be noted that the nonlinear high-dimensional spatiotemporal problem is transformed into a partially observable Markov decision process. Fuzzy control theory is used to reduce the dimensionality of the high-dimensional nonlinear spatiotemporal model, clean the data in the high-dimensional spatiotemporal environment, and combine case-based learning (CBL) and real-time data to determine relevant parameters such as delay time and dimensionality.

[0045] By comparing historical case data models stored in the case knowledge base with nonlinear high-dimensional spatiotemporal models, N similar cases are selected through a similarity model. The model is then trained using case knowledge and real-time data, and the effects of different relevant parameter configurations are evaluated to find the optimal relevant parameter configuration.

[0046] This application uses chaotic phase space reconstruction to solve the nonlinear and spatiotemporally high-dimensional problems in the transportation system; it uses real-time traffic flow data, traffic statistics data in different time periods, and vehicle idle status data as input vectors, extracts successful cases from the case data knowledge base, and automatically selects appropriate strategies.

[0047] The process requires determining two parameters: the input dimension d and the delay time τ (time lag). The traffic data attribute parameters are evaluated using a case data knowledge base, and the dimension d is determined using the "false nearest neighbor method" and the delay time τ is determined using the "mutual information method".

[0048] In d-dimensional phase space:

[0049] Let a1(i,d)=‖x(i+dτ)-x(n(i,d)+dτ)‖2 / R d (t), if a1(i,d)>R τ If ∈[10,50], then y n(i,d) (d) is y i The spurious nearest point of (d), where R is... τ This represents the threshold, y i (d)=x(i),…,x(i+(d-1)τ represents any vector, y n(i,d) (d) is y i (d) is the Euclidean nearest neighbor, and R d (t) represents this distance.

[0050] For the measured time series, the dimension m starts from 2. R=30 is used to calculate the proportion of false nearest neighbors. Then m is increased until the proportion of false nearest neighbors is less than 5% or the number of false nearest neighbors no longer decreases with the increase of m. At this point, m can be considered a suitable embedding dimension.

[0051] For two discrete information systems {S1,…,S}, a transportation network and an energy network, m},{Q1,…,Q m The systems S and Q constituted by}

[0052] According to the "mutual information method":

[0053] Now we define (S,Q) = (x(i),x(i+τ)), where 1≤i≤n-τ, meaning S represents time x(i) and Q represents time x(i+τ). Then I(S,Q) is a function of the delay time τ, which can be written as I(τ). The magnitude of I(τ) represents the determinism of system Q (x(i+τ)) given system S, i.e., x(i). I(τ) = 0 indicates that x(i) and x(i+τ) are completely unpredictable, meaning they are completely uncorrelated. The first minimum value of I(τ) indicates that x(i) and x(i+τ) are most likely uncorrelated, and the first minimum value of I(τ) is the optimal delay time τ for reconstruction.

[0054] Further matrix operations and feature extraction are performed (e.g., using NumPy to calculate statistical features of time-series information (such as mean, variance, and covariance) and features of spatial information (traffic flow, vehicle speed, and vehicle restriction status)). Then, deep learning models are used to build training and contrast environments to automatically encode or reduce the dimensionality of the features, thereby better representing the traffic flow status.

[0055] S105. Establish a predictive model to assess the traffic flow status and energy supply and exchange facility service level within the future planning area, and use an optimization algorithm to filter from the feasible decision set based on the assessment results and strategy parameters to obtain multiple optimal decisions.

[0056] In other words, optimization algorithms are used to optimize the multi-objective function descriptor of the prediction model established above, thereby obtaining multiple optimal decision choices; in particular, the optimization algorithms include value-based metaheuristic optimization methods, policy-based sequential reinforcement learning optimization methods, and model-based end-to-end machine learning optimization methods.

[0057] Specifically, the standardization method for selecting multi-objective fitness functions, known as the objective standard method, combines all objective functions into a weighted objective function. While the format of the descriptors for multiple objective functions is fixed, the specific combination is uncertain when the weighting values ​​are not determined. In this case, various optimization objective functions are pre-stored in a customized graph to form a knowledge graph. Semantic associations are performed during the decision-making process to select appropriate objective data descriptors to form the fitness function for decision-making. The graph form represents the description of each optimization objective and its default weighting values. The structured descriptors include type, attributes, and methods. After being extracted from the graph, they form entities. Different entities are related to each other, and the attributes of the entities contain weight information. A weight of 0 indicates no participation in optimization, 0-1 indicates weighting in this multi-objective optimization, and 1 indicates participation in the multi-objective optimization. Features are extracted from the descriptors of the multi-objective function for optimizing the location of energy supply and energy exchange facilities (including charging time, number of charging sessions, traffic flow, population density, land price, distribution density and coverage of energy supply and energy exchange facilities, grid connection capacity, etc.). By using the multi-objective fitness function descriptors such as charging time, number of charging sessions, traffic flow, population density, land price, distribution density and coverage of energy supply facilities, grid connection capacity, etc., as attributes of the two major entities of traffic flow and energy flow in the table, different default weights are assigned and stored in a customized graph. Based on the environment of the evaluated energy supply and energy exchange facilities, the system automatically presets and selects descriptors with higher fitness to form an optimal weighted objective function to evaluate and decide on the optimization problem, thereby obtaining multiple decision options.

[0058] As a specific example, such as Figure 2 As shown, in constructing the transportation-energy supply and exchange infrastructure system model, it is assumed that there are two existing energy supply and exchange infrastructure sites within the environmental area, along with various modes of transportation within the area. The energy supply capacity of each of the two existing energy supply and exchange infrastructure sites is R. a Each power supply duration t i Each has its own energy supply frequency m, while the traffic flow under normal operating conditions for various modes of transportation within the region is Q. CTraffic density ρ, vehicle speed v, number of reported vehicle idle status n and duration t are used to compare the traffic operation level and facility service level in the region after the optimization and construction of energy supply and swapping infrastructure. Information communication and interaction between new energy vehicles, traffic infrastructure and energy supply and swapping infrastructure in the region are established. Demand growth in the region is constrained by a certain threshold, and future demand changes are predicted to carry out optimization tasks.

[0059] Based on the above model, the optimization strategy mainly depends on the predicted traffic flow status and the service level index of the energy supply and exchange infrastructure. Therefore, traffic flow operation efficiency and the service level of the energy supply and exchange infrastructure can be considered to effectively optimize the existing infrastructure deployment. By jointly optimizing two parameters—traffic state operation level and facility service level—with the goal of minimizing the operation service level under energy consumption constraints, and assuming that traffic prediction and energy supply and exchange site selection decisions can be carried out simultaneously, an optimization problem is proposed.

[0060] The obtained nonlinear high-dimensional spatiotemporal model problem is transformed into a partially observable Markov decision process. Based on metaheuristics, a pre-defined multi-objective function descriptor is applied to automatically combine the best multi-objective fitness function to obtain multiple optimal decision optimization choices.

[0061] Specifically, two state spaces are defined to represent traffic state S1 and energy supply and swapping infrastructure service state S2, respectively:

[0062]

[0063] Define the traffic flow prediction reward function:

[0064]

[0065] In the formula, The above model establishes a predicted traffic growth rate, where N represents the actual traffic volume of traffic flow, V represents the maximum service traffic volume under baseline conditions, and T... i Let m be the total usage time of the i-th power supply and energy exchange facility, and m be the total number of times the i-th power supply and energy exchange facility is used.

[0066] Basic traffic capacity:

[0067]

[0068] In the formula, v is the driving speed, t0 is the minimum headway, and l0 is the minimum headway.

[0069]

[0070] In the formula, l c l is the average length of the vehicle. a For the safe distance between vehicles, l zFor vehicle braking distance, l f The distance the vehicle travels within the driver's reaction time.

[0071] Many factors affect road conditions and traffic capacity. Generally, the factors with the greatest impact are considered, and their correction coefficients are as follows: lane width correction coefficient Y1; lateral clearance correction coefficient Y2; longitudinal slope correction coefficient Y3; insufficient sight distance correction coefficient Y4; and roadside conditions correction coefficient Y5.

[0072] Traffic condition corrections mainly refer to the composition of vehicles, especially in mixed traffic situations where there are many types of vehicles of varying sizes, occupying different road areas, with different performance and speeds, resulting in significant mutual interference and severely impacting road capacity. The traffic condition correction factor is generally denoted as Y6.

[0073] The actual traffic capacity of the road section is:

[0074] C = N max Y1Y2Y3Y4Y5Y6 (vehicles / hour)

[0075] Maximum service traffic volume:

[0076] V=(k×v×f) / m

[0077] In the formula, V represents the maximum service traffic volume under the baseline conditions, k represents the number of lanes, v represents the average speed of the lane, f represents the traffic flow of the lane, and m represents the lane capacity.

[0078]

[0079] In the formula, V is the maximum service traffic volume under the baseline conditions, C is the actual traffic capacity, and θ is the traffic flow service level.

[0080]

[0081] In the formula, n represents the number of energy exchange facilities, and t i Let m be the total usage time of the i-th power supply and exchange facility, m be the total number of times the i-th power supply and exchange facility is used, and t be the total usage time of the i-th power supply and exchange facility. j Let a be the duration of the j-th energy exchange by the i-th energy exchange facility. k For the demand assessment of the k-th energy supply and exchange facility, q is the number of energy supply and exchange facilities in the region, and r is the number of energy supply and exchange facilities. k For the traffic flow of the k-th energy exchange facility, s k For the scale of the k-th energy exchange facility, l k This data is for assessing the energy demand in the region.

[0082] Define action function a t :

[0083]

[0084] Critic function:

[0085] θ≤θ0

[0086] l k ≥l0

[0087] T≤T0

[0088] Traffic flow service level:

[0089] 0≤θ≤0.75

[0090] Energy exchange facility requirements:

[0091] l k ≥l0

[0092] T≤T0

[0093] Where θ represents the traffic flow service level, and θ0 represents the minimum service level during stable traffic flow operation, typically ranging from 0 to 0.75. k This represents the demand data for energy supply and energy exchange facilities, with l0 representing the minimum demand for these facilities.

[0094] Further, using traffic flow status data and energy exchange facility demand data as constraints, data on energy exchange facilities with traffic flow service levels below a threshold and energy exchange facility duration demand data above a threshold within the region are selected as valid data. Based on the traffic flow service level data threshold and the energy exchange facility duration demand data threshold, energy exchange facility data that meets the conditions is filtered out. Data on energy exchange facilities that do not meet the traffic flow service level data threshold and the energy exchange facility duration demand data threshold are deleted from the original data, and the location information of energy exchange facilities in the regional data is updated.

[0095] Then, optimization algorithms are used to optimize the model parameters, and the optimal strategy is learned through repeated iterations and trial and error. Simultaneously, model parameter optimization and hyperparameter tuning algorithms are performed to find the best combination of model parameters. The model's output is compared with actual traffic flow data, and its performance is measured according to evaluation metrics. Once the model training and optimization are complete, it can be used for real-time traffic flow prediction (requiring real-time updates to the model's input data and output of predicted traffic flow status).

[0096] Further optimization algorithms are used, with transportation and energy as the two main entities. The attribute weights of these two entities are preset and stored in a pre-defined table. For site selection problems influenced by different factors, a suitable fitness function is selected based on the preset attributes to search for the global optimum. Specifically, the specific graphical representation is as follows: Figure 4 As shown.

[0097] S106, sort the multiple optimal decisions by their rank-sum ratios to obtain the final decision result.

[0098] As an example, ranking multiple optimal decisions by rank-sum ratio includes: calculating the rank-sum ratio of multiple optimal decisions based on the benefit index from smallest to largest; obtaining the dimensionless statistic RSR value through rank transformation; and ranking the multiple optimal decisions by RSR value, wherein a higher RSR value corresponds to a better performance in terms of cost, and a lower RSR value corresponds to a worse performance in terms of cost.

[0099] In other words, multiple optimal decisions are ranked according to the benefit indicators from smallest to largest, and the rank-sum ratio is calculated. Through rank transformation, the dimensionless statistic RSR is obtained. The RSR values ​​are used to directly rank or classify the multiple optimal decisions based on their merits, and suitable construction points are selected for construction.

[0100] The specific calculation methods for some RSR values ​​are shown below:

[0101]

[0102]

[0103] As an example, the site selection decision method for energy supply and swapping facilities for new energy vehicles also includes obtaining the corresponding construction site for the energy supply and swapping facilities based on the final decision result, and storing the corresponding traffic flow data and energy supply and swapping facility data in the case data knowledge base after construction is carried out at the construction site.

[0104] In other words, based on the feedback from the optimization results, the operational status after site optimization is recorded, the service performance after optimization is evaluated, and this information is recorded in the case data knowledge base. Specifically, after site optimization, feedback on the optimization results is collected through various channels, including user feedback, service level logs of the energy supply and swapping infrastructure, and traffic flow monitoring data. Detailed records are kept of all parameters, execution time, and resource usage involved in the site optimization process. Based on the collected feedback and the recorded operational status after site optimization, the service performance after optimization is evaluated. Key evaluation indicators include traffic efficiency, utilization level of the energy supply and swapping infrastructure, and user satisfaction. Based on the evaluation results, optimizations are implemented for any areas with poor performance. The entire process is recorded in the case data knowledge base.

[0105] In summary, the site selection decision method for new energy vehicle energy supply and swapping facilities according to the embodiments of this application constructs a site selection model for energy supply and swapping facilities in an energy demand-traffic prediction fusion scenario. This model applies traffic data and traffic cell nodes to a nonlinear high-dimensional spatiotemporal model. Under the constraints of discrete traffic flow and energy distribution, it considers factors such as energy supply and swapping duration, frequency, traffic flow, pedestrian density, land price, distribution density and coverage of energy supply and swapping facilities, and grid connection capacity, aiming for the optimal service level. Furthermore, under a traffic spatiotemporal model established using fuzzy control theory, a predictive model for traffic flow and the service level of energy supply and swapping facilities within the region is established and trained. This comprehensively considers the combined index of road traffic operation levels and energy supply and swapping facility usage levels before and after optimization, and utilizes a pre-stored multi-objective fitness function to describe... The descriptor automatically sets the weights of multi-objective functions under different scenarios to train the model and evaluate the effects of different descriptor configurations in order to find the optimal weighted multi-objective function. In practice, table pre-setting and real-time optimization can be used in combination to improve optimization performance, making the site selection strategy for power supply and energy conversion facilities more stable and efficient. Multiple optimal decisions obtained based on optimization algorithms are used, and the rank-sum ratio calculation and ranking method is combined to optimize the multi-objective order of multiple optimal decisions, making the final site selection optimization service more reasonable and achieving higher economic and social benefits. Data is processed using a data knowledge fusion approach, and a knowledge graph is established based on the knowledge under existing traffic laws and construction deployment constraints. This knowledge is semantically associated with real-time traffic data for decision-making, providing a more comprehensive and accurate data view, thereby obtaining more accurate decisions.

[0106] To achieve the above embodiments, this application proposes a site selection decision device for energy supply and swapping facilities for new energy vehicles, such as... Figure 5 As shown, the site selection decision device for new energy vehicle power supply and swapping facilities proposed in this application includes: a data acquisition module 10, a partitioning module 20, a generation module 30, a processing module 40, and an optimized site selection module 50.

[0107] Among them, the data acquisition module 10 is used to acquire traffic flow data and energy supply and conversion facility data within the planning area;

[0108] In other words, various traffic status data, vehicle status data, and service status data of power supply and energy conversion facilities are collected through the data acquisition module 10 to form structured data; the data collection sources include reports from vehicle-mounted equipment and satellite-mounted equipment, reports from roadside units, and shared data from networked operation platforms.

[0109] The division module 20 is used to divide the planning area according to traffic flow data and power supply and exchange facility data to obtain multiple traffic zones;

[0110] In other words, the segmentation module 20 divides traffic zones based on the various spatiotemporal state data collected and uses a clustering method to obtain a data association graph with spectral stability. In particular, the clustering method can adopt spectral clustering of graph signal processing, which regards each object in the dataset as a vertex of the graph and measures the similarity between vertices as the weight of the edge connecting the corresponding vertices, thus transforming the clustering problem into a graph segmentation problem and constructing traffic zone division.

[0111] The generation module 30 is used to establish a nonlinear high-dimensional spatiotemporal model of traffic flow data and traffic zones using fuzzy control theory, and to obtain a set of feasible decisions for potential energy supply and exchange facility construction sites using the nonlinear high-dimensional spatiotemporal model.

[0112] In other words, by generating 30 pairs of interrelated traffic flow data and spatiotemporal data of energy supply and conversion facilities, and matching them with the divided traffic zones, a nonlinear high-dimensional spatiotemporal model in three-dimensional space is generated; and a set of potential construction site planning is obtained.

[0113] The processing module 40 is used to perform dimensionality reduction processing on the nonlinear high-dimensional spatiotemporal model and obtain appropriate strategy parameters by combining the case data knowledge base;

[0114] In other words, by using appropriate fuzzy control techniques, several case knowledge items sorted by similarity in the case knowledge base are extracted, and a suitable optimization strategy is automatically selected. Furthermore, based on the selected optimization strategy and real-time data, a prediction model matches relevant parameters from the case knowledge base and selects preset hyperparameters from the knowledge graph to obtain traffic-energy conversion facility data for a future period. The case data knowledge base stores historical cases, cases sharing neighbor nodes, and successfully updated cases; it also stores and extracts algorithmic knowledge and stores and retrieves the graph structure data of the knowledge graph.

[0115] The site selection optimization module 50 is used to establish a prediction model to evaluate the traffic flow status and energy supply and exchange facility service level in the future planning area, and to select from the feasible decision set using an optimization algorithm based on the evaluation results and strategy parameters to obtain multiple optimal decisions; the multiple optimal decisions are sorted by rank and ratio to obtain the final decision result.

[0116] In other words, the site selection optimization module 50 automatically combines a pre-set multi-objective fitness function descriptor knowledge graph into an optimal weighted evaluation function to evaluate the traffic data and energy supply and conversion facility data within the region. Based on the optimization algorithm, the module iteratively selects the optimal decision by setting a threshold, and finally selects the optimal decision by ranking the rank-sum ratio.

[0117] As an example, it also includes an update module, which is used to obtain the corresponding energy supply and exchange facility construction point according to the final decision result, and store the corresponding traffic flow data and energy supply and exchange facility data in the case data knowledge base after construction is carried out at the construction point.

[0118] In other words, the update module stores the traffic flow data, vehicle status data, energy supply and exchange facility service data, and various optimization strategy parameter updates processed by the mobile phone in the case data knowledge base.

[0119] As an example, the processing module is also used to perform dimensionality reduction processing on the nonlinear high-dimensional spatiotemporal model using fuzzy control technology; compare the historical case data model stored in the case data knowledge base with the nonlinear high-dimensional spatiotemporal model to filter out similar cases; and obtain appropriate strategy parameters based on the similar cases.

[0120] As an example, the site selection optimization module is also used to calculate the rank-sum ratio of multiple optimal decisions based on the benefit index from smallest to largest; obtain the dimensionless statistic RSR value through rank transformation, and rank the multiple optimal decisions based on the RSR value, wherein the higher the RSR value, the better the decision performs in terms of cost, and the lower the RSR value, the worse the decision performs in terms of cost.

[0121] It should be noted that the explanation of the above-mentioned method for site selection decision of energy supply and swapping facilities for new energy vehicles also applies to the site selection decision device for energy supply and swapping facilities for new energy vehicles in this embodiment, and will not be repeated here.

[0122] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0123] The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0124] When the processor 602 executes the program, it implements the site selection decision method for energy supply and swapping facilities for new energy vehicles provided in the above embodiments.

[0125] Furthermore, electronic devices also include:

[0126] Communication interface 603 is used for communication between memory 601 and processor 602.

[0127] The memory 601 is used to store computer programs that can run on the processor 602.

[0128] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0129] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0130] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0131] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0132] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for site selection decision of energy supply and swapping facilities for new energy vehicles.

[0133] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0134] Furthermore, 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 at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0135] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0136] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0137] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0138] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0139] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0140] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for site selection of energy supply and swapping facilities for new energy vehicles, characterized in that, Includes the following steps: Obtain traffic flow data and energy supply and conversion facility data within the planning area; The planning area is divided into multiple traffic zones based on the traffic flow data and energy supply and exchange facility data. A nonlinear high-dimensional spatiotemporal model of the traffic flow data and the traffic zone is established using fuzzy control theory, and the feasible decision set of potential energy supply and exchange facility construction sites is obtained using the nonlinear high-dimensional spatiotemporal model. The nonlinear high-dimensional spatiotemporal model is subjected to dimensionality reduction processing, and appropriate strategy parameters including embedding dimension and delay time are obtained by combining case data knowledge base. The embedding dimension is determined by the false nearest neighbor method, and the delay time is determined by the mutual information method. A predictive model is established to assess the traffic flow status and energy supply and exchange facility service level in the future planning area. Based on the assessment results and the strategy parameters, an optimization algorithm is used to filter the feasible decision set to obtain multiple optimal decisions. The multiple optimal decisions are sorted by their rank-to-ratio to obtain the final decision result.

2. The site selection decision method for energy supply and swapping facilities for new energy vehicles as described in claim 1, characterized in that, Also includes: Based on the final decision result, the corresponding energy supply and exchange facility construction points are obtained, and after construction is carried out at the construction points, the corresponding traffic flow data and energy supply and exchange facility data are stored in the case data knowledge base.

3. The site selection decision method for new energy vehicle energy supply and swapping facilities as described in claim 1, characterized in that, The nonlinear high-dimensional spatiotemporal model is subjected to dimensionality reduction processing, and suitable policy parameters, including embedding dimension and delay time, are obtained by combining the case data knowledge base. Fuzzy control technology is used to reduce the dimensionality of the nonlinear high-dimensional spatiotemporal model. The historical case data model stored in the case data knowledge base is compared with the nonlinear high-dimensional spatiotemporal model to filter out similar cases; Based on the similar cases, appropriate policy parameters, including embedding dimension and delay time, are obtained.

4. The site selection decision method for new energy vehicle energy supply and swapping facilities as described in claim 1, characterized in that, The ranking of the multiple optimal decisions by their rank-sum ratio includes: For multiple optimal decisions, calculate the rank-sum ratio based on the benefit indicators from smallest to largest; The dimensionless statistic RSR value is obtained by rank transformation. Multiple optimal decisions are ranked by RSR value. The higher the RSR value, the better the decision performs in terms of cost, and the lower the RSR value, the worse the decision performs in terms of cost.

5. A site selection decision device for energy supply and swapping facilities for new energy vehicles, characterized in that, include: The data acquisition module is used to acquire traffic flow data and energy exchange facility data within the planning area; The segmentation module is used to segment the planning area based on the traffic flow data and the power supply and energy conversion facility data to obtain multiple traffic zones; The generation module is used to establish a nonlinear high-dimensional spatiotemporal model of the traffic flow data and the traffic zone using fuzzy control theory, and to obtain a feasible decision set of potential energy supply and exchange facility construction sites using the nonlinear high-dimensional spatiotemporal model. The processing module is used to perform dimensionality reduction processing on the nonlinear high-dimensional spatiotemporal model and obtain policy parameters including embedding dimension and delay time by combining case data knowledge base. The embedding dimension is determined by the false nearest neighbor method and the appropriate policy parameters for the delay time are determined by the mutual information method. The site selection optimization module is used to establish a predictive model to evaluate the traffic flow status and energy supply and exchange facility service level in the future planning area, and to use an optimization algorithm to filter the feasible decision set according to the evaluation results and the strategy parameters to obtain multiple optimal decisions; the multiple optimal decisions are sorted by rank-sum ratio to obtain the final decision result.

6. The site selection decision device for energy supply and swapping facilities for new energy vehicles as described in claim 5, characterized in that, Also includes: The update module is used to obtain the corresponding energy supply and exchange facility construction points based on the final decision result, and after construction is carried out at the construction points, store the corresponding traffic flow data and energy supply and exchange facility data into the case data knowledge base.

7. The site selection decision device for new energy vehicle energy supply and swapping facilities as described in claim 5, characterized in that, The processing module is also used for: Fuzzy control technology is used to reduce the dimensionality of the nonlinear high-dimensional spatiotemporal model. The historical case data model stored in the case data knowledge base is compared with the nonlinear high-dimensional spatiotemporal model to filter out similar cases; Based on the similar cases, appropriate policy parameters, including embedding dimension and delay time, are obtained.

8. The site selection decision device for new energy vehicle energy supply and swapping facilities as described in claim 5, characterized in that, The optimized address selection module is also used for: For multiple optimal decisions, calculate the rank-sum ratio based on the benefit indicators from smallest to largest; The dimensionless statistic RSR value is obtained by rank transformation. Multiple optimal decisions are ranked by RSR value. The higher the RSR value, the better the decision performs in terms of cost, and the lower the RSR value, the worse the decision performs in terms of cost.

9. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the site selection decision method for energy exchange facilities for new energy vehicles as described in any one of claims 1-4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the site selection decision method for energy supply and swapping facilities for new energy vehicles as described in any one of claims 1-4.

Images