Electric vehicle path planning method based on multi-source data fusion

Abstract

The invention discloses an electric vehicle path planning method based on multi-source data fusion, and relates to the technical field of path planning, and the method comprises the steps: fusing a historical equivalent length and a real-time equivalent length, and obtaining the comprehensive equivalent length of each line and a line adjacency matrix of a traffic road network; and based on the comprehensive equivalent length and the line adjacency matrix, obtaining an optimal path according to a path starting point and an end point determined by a user. According to the method, the comprehensive equivalent length and the line adjacency matrix of the traffic road network are obtained by fusing the historical equivalent length based on the historical traffic data and the real-time equivalent line length based on the real-time traffic data, and the real-time road condition information and the historical traffic information are combined; according to the method, the optimal path capable of considering the real-time congestion condition of the traffic road and historical user driving habits is obtained, faster and more efficient arrival from the starting point to the end point is realized, and the passing efficiency of a traffic road network is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and more specifically, to a method for electric vehicle path planning based on multi-source data fusion. Background Technology

[0002] With the rapid pace of social development and urbanization, transportation systems are facing increasingly severe pressure and challenges. Especially with the rapid popularization of electric vehicles, the load on urban road networks continues to increase, traffic structures are becoming more complex, and traffic congestion is becoming more frequent, resulting not only in a significant waste of time but also reduced energy efficiency. Therefore, optimizing traffic management and improving road traffic efficiency have become critical issues that urgently need to be addressed in current urban development.

[0003] In recent years, advancements in intelligent transportation technology have offered new possibilities for achieving efficient traffic management. With the help of various sensing devices and data processing technologies, the collection and application of real-time traffic information have gradually matured. However, the massive amounts of real-time information and complex road environments place higher demands on dynamic route planning. While existing technologies can acquire real-time traffic data, they still have shortcomings in integrating and analyzing historical vehicle behavior characteristics with immediate traffic information, thus limiting the accuracy and practicality of route planning strategies.

[0004] Against this backdrop, effectively integrating historical vehicle driving data with real-time traffic conditions to construct a more accurate and adaptable route planning method is of great significance for improving the overall efficiency of intelligent transportation systems and has become a research direction worthy of in-depth exploration in this field. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide an electric vehicle path planning method based on multi-source data fusion, which solves the problem of how to effectively avoid road congestion during vehicle operation.

[0006] To achieve the above objectives, embodiments of the present invention provide an electric vehicle path planning method based on multi-source data fusion, comprising: Historical traffic data of the road network is collected, and hierarchical clustering is used to obtain the historical equivalent length of each section of the route. Collect real-time traffic data of the road network to obtain the real-time equivalent line length of each section of the road and each intersection; By integrating the historical equivalent length and the real-time equivalent length, the comprehensive equivalent length of each line segment and the line adjacency matrix of the traffic road network are obtained. Based on the comprehensive equivalent length and the line adjacency matrix, the optimal path is obtained according to the path start point and end point determined by the user.

[0007] In a preferred embodiment, the collected historical traffic data includes: the number of vehicles in historical traffic, average speed, and travel time.

[0008] In a preferred embodiment, the hierarchical clustering obtains the historical equivalent length of each line segment, including: Hierarchical clustering is performed on the historical traffic data to obtain the congestion level of each segment of the road network. Based on the congestion level, the congestion coefficient corresponding to each line segment is obtained; Based on the congestion coefficient, the historical equivalent length of each line segment is obtained.

[0009] In a preferred embodiment, hierarchical clustering is performed on the historical traffic data, specifically: Cluster the various segments of the transportation road network to obtain clustered route clusters; Based on the aforementioned route clusters, the congestion levels of each segment of the traffic road network are classified.

[0010] In a preferred embodiment, the step of collecting real-time traffic data of the road network to obtain the real-time equivalent line length of each road segment and intersection includes: Based on the real-time traffic data of the aforementioned road network, the saturation of each route segment is calculated; The saturation is divided into several saturation intervals to obtain the corresponding saturation levels; Based on the saturation level, calculate the real-time equivalent line length of each line segment; Calculate the real-time equivalent line length of each intersection based on the real-time equivalent line length of each line segment.

[0011] In a preferred embodiment, the historical equivalent length and the real-time equivalent length are fused to obtain the comprehensive equivalent length of each line segment and the line adjacency matrix of the traffic road network, including: Based on the historical equivalent length of each route segment, combined with the real-time equivalent length of each route segment and each intersection, and according to the traffic topology of the road network, the comprehensive equivalent length of each route segment is obtained. By combining the combined equivalent lengths of each line segment at the same time, the line adjacency matrix of the traffic road network is obtained.

[0012] In a preferred embodiment, when obtaining the optimal path based on the user-determined starting and ending points of the path, the Dijkstra greedy algorithm is used to calculate the shortest path from the starting point to the ending point in the traffic road network based on the comprehensive equivalent length and the line adjacency matrix, and the shortest path is output as the optimal path.

[0013] In a preferred embodiment, the step of using Dijkstra's greedy algorithm to calculate the shortest path from the starting point to the ending point in the traffic road network specifically involves: Label each intersection in the traffic road network and define the set of intersections with determined shortest paths and the set of intersections with undetermined shortest paths. Initialize the set of intersections, and initialize the starting point, all intersections except the starting point, and the current intersection; Iterate through the adjacent intersections connected to the current intersection, calculate the equivalent length of the new path and update the equivalent length of the original path, until the shortest path from the starting point to the ending point is obtained.

[0014] In a preferred embodiment, the process involves traversing adjacent intersections connected to the current intersection, calculating the equivalent length of the new path, and updating the equivalent length of the original path, including: Calculate the combined equivalent length between the current intersection and its adjacent intersections; Based on the equivalent path length from the starting point to the current intersection, calculate the equivalent path length from the starting point to the intersection adjacent to the current intersection. The equivalent length of the original path is compared with the equivalent length of the new path, and the equivalent length of the original path is updated to the minimum value between the equivalent length of the original path and the equivalent length of the new path.

[0015] In a preferred embodiment, when obtaining the shortest path from the starting point to the ending point, The set of intersections with undetermined shortest paths is empty and / or the user-defined destination is added to the set of intersections with determined shortest paths.

[0016] The beneficial effects of this invention are: By integrating historical equivalent lengths based on historical traffic data with real-time equivalent route lengths based on real-time traffic data, a comprehensive equivalent length and a route adjacency matrix of the traffic road network are obtained. Based on the user-defined starting and ending points, and combined with real-time traffic information and historical traffic information, the optimal path is obtained that takes into account both real-time traffic congestion and historical user driving habits, enabling faster and more efficient travel from the starting point to the destination, and greatly improving the traffic efficiency of the traffic road network. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating an electric vehicle route planning method based on multi-source data fusion. Figure 2 A flowchart illustrating the process for obtaining the historical equivalent length; Figure 3 A flowchart illustrating the process of obtaining the real-time equivalent line length. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figure 1 A method for electric vehicle route planning based on multi-source data fusion includes: collecting historical traffic data of a road network and hierarchically clustering to obtain the historical equivalent length of each route segment; collecting real-time traffic data of the road network and obtaining the real-time equivalent route length of each route segment and each intersection; fusing the historical equivalent length and the real-time equivalent length to obtain the comprehensive equivalent length of each route segment and the route adjacency matrix of the road network; and obtaining the optimal route based on the comprehensive equivalent length and the route adjacency matrix, according to the route start point and end point determined by the user.

[0020] By collecting historical traffic data from the road network separately, the historical equivalent length is obtained; by collecting real-time traffic data from the road network, the real-time equivalent route length is obtained. Then, the historical equivalent length and the real-time equivalent route length are merged to obtain the comprehensive equivalent length and the route adjacency matrix of the road network. Based on the comprehensive equivalent length and the route adjacency matrix of the road network, and according to the user-determined starting point and ending point, real-time traffic information and historical traffic information are used to reasonably avoid possible congestion during traffic, and obtain the optimal route that takes into account both the real-time traffic congestion and the historical user driving habits, so as to achieve faster and more efficient travel from the starting point to the ending point and improve the traffic efficiency of the road network.

[0021] To more accurately obtain the historical equivalent length of each segment of the road network, this implementation provides a more detailed explanation of the process of collecting historical traffic data from the road network and using hierarchical clustering to obtain the historical equivalent length of each segment, as follows: S1. Collect historical traffic data of the road network and use hierarchical clustering to obtain the historical equivalent length of each section of the route; By performing cluster analysis on the collected historical traffic data, the congestion situation on roads at various times can be obtained and used to guide real-time route planning.

[0022] S11. Collect historical traffic data for each segment of the road network: The collected historical traffic data includes: the number of vehicles, average speed, and travel time in historical traffic.

[0023] Collect data on various sections of the transportation road network. Historical traffic data for the specified time period includes: number of vehicles, average speed, and travel time. And the... intersection and the intersection The lines between In history Traffic data at any given time is recorded as follows:

[0024] In the formula, Indicates the line In history Number of vehicles at any given time; Indicates the line In history The average speed of vehicles at any given time; Indicates the line In history The average travel time of a vehicle at any given time.

[0025] S12. Perform hierarchical clustering on the historical traffic data to obtain the historical equivalent length of each route segment: Please see Figure 2 The hierarchical clustering method for obtaining the historical equivalent length of each route segment includes: performing hierarchical clustering on the historical traffic data to obtain the congestion level of each route segment in the traffic road network; obtaining the congestion coefficient corresponding to each route segment based on the congestion level; and obtaining the historical equivalent length corresponding to each route segment based on the congestion coefficient.

[0026] S121. Perform hierarchical clustering on historical traffic data to obtain the congestion level of each segment of the road network: Hierarchical clustering is performed on the historical traffic data, specifically: each segment of the road network is clustered to obtain clustered route clusters; based on these route clusters, the congestion level of each segment of the road network is classified. That is: Hierarchical clustering method for historical Historical traffic data for each segment of the route at any given time are clustered to obtain S clusters of routes, thus representing the historical data. All lines at any given time are divided into S congestion levels; in this example, S=4 is selected, which means that user behavior data is clustered into four line clusters.

[0027] S122. Based on the congestion level, obtain the congestion coefficient corresponding to each line segment: Based on the defined congestion levels, the congestion coefficient for each route segment is determined, and a weighted path planning method is used to quantify the impact of different congestion levels on vehicle operation. Specifically: Assuming the route In history The congestion level corresponding to time s is the s-th congestion level, and Then define the line with the s-th congestion level. In history Congestion coefficient at any time for:

[0028] In the formula: For routes where vehicles can pass normally when there is no congestion Time; Let be the set of lines included in the s-th congestion level.

[0029] S123. Based on the congestion coefficient, obtain the historical equivalent length corresponding to each line segment: To better describe the congestion level of each line segment, a congestion coefficient is used to correct for the congestion level of each segment. That is, an equivalent line length is defined, which reflects the impact of the congestion level of each line segment on vehicle operation. In history Equivalent length of the line at any given time for:

[0030] In the formula: For the line The actual length.

[0031] By collecting historical traffic data from the road network and using hierarchical clustering algorithms, each route segment is classified into multiple congestion levels at different historical times, such as smooth traffic, slow traffic, congestion, and severe congestion, thereby quantifying the historical congestion tendency of each route segment at a specific time. Based on the congestion level, a congestion coefficient based on historical traffic data is defined for each route segment and converted into a historical equivalent length, providing a scientific basis for subsequent prediction of congestion conditions of each route segment based on historical traffic data.

[0032] To more accurately obtain the real-time equivalent route length of each segment of the road network, this implementation provides a more detailed explanation of the collection of real-time traffic data from the road network to obtain the real-time equivalent route length of each segment and intersection, as follows: S2. Collect real-time traffic data of the road network to obtain the real-time equivalent route length of each road segment and intersection: Please see Figure 3The method of collecting real-time traffic data of the road network and obtaining the real-time equivalent line length of each line segment and each intersection includes: calculating the saturation of each line segment based on the real-time traffic data of the road network; dividing the saturation into several saturation intervals to obtain the corresponding saturation level; calculating the real-time equivalent line length of each line segment based on the saturation level; and calculating the real-time equivalent line length of each intersection based on the real-time equivalent line length of each line segment.

[0033] Based on the collected real-time traffic data of the road network, a real-time equivalent line length based on the speed-flow model is established to describe the relationship between the equivalent length of each line segment and the traffic flow.

[0034] S21. Based on real-time traffic data of the road network, calculate the saturation of each route segment: No. intersection and the intersection The lines between exist Saturation at any moment for:

[0035] in, In the formula, for Timetable Actual traffic volume; for Timetable The capacity; To be in the historical moment The corresponding current moment.

[0036] S22. Divide the saturation into several saturation intervals to obtain the corresponding saturation levels: Saturation Divide into C saturation intervals in sequence: , ... ... ,in, This represents the c-th saturation interval.

[0037] C saturation levels are determined by C saturation intervals. In this example, C=4 is selected, that is, the line saturation is divided into four intervals, corresponding to four line saturation levels. The intervals are [0-0.3), [0.3-0.5), [0.5-0.8), and [0.8-1.0].

[0038] S23. Based on the saturation level, calculate the real-time equivalent line length for each line segment: Assuming the route exist If the saturation level corresponding to time c is the c-th saturation level, then the th... intersection and the intersection The lines between exist Equivalent line length at time for:

[0039] In the formula, , The lines are respectively The two line saturation coefficients are:

[0040]

[0041] S24. Based on the real-time equivalent line length of each line segment, calculate the real-time equivalent line length of each intersection: The first in the transportation road network intersection exist Equivalent line length at time for:

[0042] In the formula, yes Time of the first intersection The speed of vehicle traffic; It is the first intersection Speed ​​correction factor; For the first intersection The traffic light cycle; For the first intersection The percentage of green time on traffic lights; For the first intersection Vehicle arrival rate; The critical value for saturation is calculated as follows:

[0043] In the formula, The number of roads included in the c-th saturation level; This is the lower bound of the c-th saturation interval; This is the upper bound of the c-th saturation interval.

[0044] By collecting real-time traffic data from the road network, the saturation level of each road segment at the current moment is calculated as the ratio of actual traffic flow to design capacity, and the segments are also classified into levels. Then, using a speed-flow model, the real-time saturation level is converted into the real-time equivalent road length. Taking into account factors such as the traffic light cycle and the percentage of green lights at intersections, the real-time equivalent road length of the intersection is also calculated, accurately reflecting the traffic delay at the intersection.

[0045] To balance historical traffic behavior characteristics with actual road condition information, this embodiment integrates historical and real-time equivalent lengths to obtain the comprehensive equivalent length of each route segment and the route adjacency matrix of the traffic road network, effectively improving the accuracy and practicality of subsequent route home navigation. Specifically: S3. By integrating historical equivalent lengths and real-time equivalent lengths, the comprehensive equivalent length of each line segment and the line adjacency matrix of the traffic road network are obtained: By integrating the historical equivalent length and the real-time equivalent length, the comprehensive equivalent length of each route segment and the route adjacency matrix of the traffic road network are obtained. This includes: obtaining the comprehensive equivalent length of each route segment based on the historical equivalent length of each route segment, combined with the real-time equivalent length of each route segment and each intersection, and according to the traffic topology of the traffic road network; and combining the comprehensive equivalent lengths of each route segment at the same time to obtain the route adjacency matrix of the traffic road network. That is: Assume all routes are two-way streets, and the routes In history The congestion level corresponding to time s is the s-th congestion level, and Based on the traffic topology of the road network, then the first... intersection and the intersection The lines between exist Comprehensive equivalent length of time for:

[0046] In the formula, For the first intersection and the intersection The lines between exist The overall equivalent length of time; A collection of routes in a transportation road network; A collection of intersections in a road network; for The first in the time-based traffic road network intersection The equivalent line length.

[0047] The comprehensive equivalent length of each segment of the transportation road network By combining these elements, we obtain the transportation road network. Line adjacency matrix at time .

[0048] By integrating historical equivalent lengths and real-time equivalent lengths, a comprehensive equivalent length for route planning is generated. This comprehensive equivalent length combines historical congestion patterns with actual traffic conditions, which can greatly reduce the time cost of traffic operations.

[0049] Based on the obtained comprehensive equivalent length and line adjacency matrix, this embodiment employs Dijkstra's greedy algorithm to calculate the shortest path from the starting point to the ending point in the traffic road network, using the comprehensive equivalent length and the line adjacency matrix, and outputs the shortest path as the optimal path. Specifically: S4. Use Dijkstra's greedy algorithm to calculate the shortest path from the starting point to the ending point in the traffic road network. This shortest path is the optimal path from the starting point to the ending point.

[0050] The method of using Dijkstra's greedy algorithm to calculate the shortest path from the starting point to the ending point in the traffic road network is as follows: Each intersection in the traffic road network is labeled, and a set of intersections with a determined shortest path and a set of intersections with an undetermined shortest path are defined respectively; the intersection sets are initialized, and the starting point, all intersections except the starting point, and the current intersection are initialized; adjacent intersections connected to the current intersection are traversed, the equivalent length of the new path is calculated, and the equivalent length of the original path is updated, until the shortest path from the starting point to the ending point is obtained.

[0051] The user determines the starting and ending points of the route planning. The Dijkstra greedy algorithm is used to calculate the shortest path from the starting point to the ending point in the traffic road network as the optimal path and output it.

[0052] S41, Initialization S411, Define Data Structure S4111, Set labels for each intersection in the road network. The first in the transportation road network intersection Use labels Mark, where, Indicates the starting point To the intersection The minimum equivalent length; Indicates the starting point To the intersection The previous intersection in the current shortest path.

[0053] S4112. Define the set of intersections for which the shortest path has been determined. Define the set of intersections for which the shortest path has been determined as follows: and initialize .

[0054] Meet at the intersection Used to store data from the starting point. To the intersection The minimum equivalent length of the intersection has been finalized and will not be changed.

[0055] S4113. Define the set of intersections where the shortest path is not determined. Define the set of intersections for which the shortest path is not determined as follows: and initialize ,in, Indicates the end point; Indicates the first One intersection.

[0056] Meet at the intersection Used to store data from the starting point. To the intersection The minimum equivalent length of the intersection has not yet been finalized.

[0057] S412, Perform initialization operations S4121. Set the intersections for which the shortest path has been determined. Initialize to an empty set, i.e. ; Set of intersections where the shortest path is not determined Initialized as a set containing all intersections in the traffic road network, i.e. ,in, Indicates the end point; Indicates the first One intersection.

[0058] S4122. Initialize the starting point: Minimum equivalent length to itself Set to 0; initialize the starting point The previous intersection .

[0059] For all other intersections except the starting point: initialize their minimum equivalent length. It is infinitely large, where, , indicating the initial state, starting from the starting point It cannot be reached directly; initialize the previous intersection to an undefined state.

[0060] S4123, Change the current operating intersection Initialize to .

[0061] S42, Update adjacent intersections Traverse the adjacent intersections connected to the current intersection, calculate the equivalent length of the new path and update the equivalent length of the original path, including: calculating the comprehensive equivalent length between the current intersection and its connected adjacent intersections; calculating the equivalent length of the new path from the starting point to the intersection adjacent to the current intersection based on the equivalent length of the path from the starting point to the current intersection; comparing the equivalent length of the original path with the equivalent length of the new path, and updating the equivalent length of the original path to the minimum value between the equivalent length of the original path and the equivalent length of the new path.

[0062] S421, Traverse adjacent intersections At the current intersection to the intersection any connected first An undetermined intersection The comprehensive equivalent length is defined as .

[0063] S422, Calculate the equivalent length of the new path. From the starting point To the current intersection The path equivalent length is Then from pass Arrival and any connected first An undetermined intersection The path equivalent length is .

[0064] S423, Update path equivalent length Compare the equivalent length of the original path Equivalent length of the new path The size between them, the equivalent length of the update path is: That is, the updated path equivalent length Equivalent length of the original path The value is equivalent to the length of the new path. The smaller value in the range.

[0065] S43. Obtain the optimal path When obtaining the shortest path from the starting point to the ending point, the set of intersections where the shortest path has not been determined is empty and / or the user-defined target endpoint is added to the set of intersections where the shortest path has been determined.

[0066] S431, Set of intersections where the shortest path has not been determined In the middle, select the intersection corresponding to the minimum value of the minimum equivalent length. As the next intersection, namely:

[0067] In the formula, Represents the set of intersections for which the shortest path is not yet determined. Intersection The corresponding minimum equivalent length; express The corresponding minimum equivalent length.

[0068] S432, From the set of intersections where the shortest path has been determined. In the middle, select the intersection Directly connected intersections, and set them equal to the intersections starting from the starting point. At the intersection Shortest path intersection The previous intersection ,Will The set of intersections whose shortest path has never been determined Delete and add to the set of intersections where the shortest path has been determined. middle.

[0069] S433. If the set of intersections for the shortest path is not determined. If empty, it means the starting point has been obtained. arrive The shortest path; otherwise, Assign to Then, step S42 is executed sequentially until the set of intersections for which the shortest path has not been determined is reached. If the value is empty and / or the destination is added to the set of intersections for which the shortest path has been determined. middle.

[0070] S434. After the algorithm ends, from the endpoint... Begin backtracking gradually until you reach the starting point of the backtracking process. Then the reverse path is the calculated shortest path; reversing the reverse path will give the path from the starting point. To the finish line The forward path, which is the starting point. To the finish line The optimal path.

[0071] By employing Dijkstra's greedy algorithm to quickly search for the optimal path from the starting point to the destination, this algorithm, based on the comprehensive equivalent length and the line adjacency matrix, integrates historical and real-time information of the traffic road network. The output optimal path planning strategy can take into account both real-time road congestion and historical user driving habits, thereby effectively improving the responsiveness and accuracy to traffic conditions and enhancing road traffic efficiency.

[0072] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0073] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0074] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0075] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0076] 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 technical scope 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.

[0077] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for electric vehicle route planning based on multi-source data fusion, characterized in that, include: Historical traffic data of the road network is collected, and hierarchical clustering is used to obtain the historical equivalent length of each section of the route. Collect real-time traffic data of the road network to obtain the real-time equivalent line length of each section of the road and each intersection; By integrating the historical equivalent length and the real-time equivalent length, the comprehensive equivalent length of each line segment and the line adjacency matrix of the traffic road network are obtained. Based on the comprehensive equivalent length and the line adjacency matrix, the optimal path is obtained according to the path start point and end point determined by the user.

2. The electric vehicle path planning method based on multi-source data fusion according to claim 1, characterized in that, The collected historical traffic data includes: the number of vehicles in historical traffic, average speed, and travel time.

3. The electric vehicle path planning method based on multi-source data fusion according to claim 1 or 2, characterized in that, The hierarchical clustering obtains the historical equivalent length of each line segment, including: Hierarchical clustering is performed on the historical traffic data to obtain the congestion level of each segment of the road network. Based on the congestion level, the congestion coefficient corresponding to each line segment is obtained; Based on the congestion coefficient, the historical equivalent length of each line segment is obtained.

4. The electric vehicle path planning method based on multi-source data fusion according to claim 3, characterized in that, Hierarchical clustering is performed on the historical traffic data, specifically: Cluster the various segments of the transportation road network to obtain clustered route clusters; Based on the aforementioned route clusters, the congestion levels of each segment of the traffic road network are classified.

5. The electric vehicle path planning method based on multi-source data fusion according to claim 4, characterized in that, The process involves collecting real-time traffic data from the road network to obtain the real-time equivalent lengths of each road segment and intersection, including: Based on the real-time traffic data of the aforementioned road network, the saturation of each route segment is calculated; The saturation is divided into several saturation intervals to obtain the corresponding saturation levels; Based on the saturation level, calculate the real-time equivalent line length of each line segment; Calculate the real-time equivalent line length of each intersection based on the real-time equivalent line length of each line segment.

6. The electric vehicle path planning method based on multi-source data fusion according to claim 5, characterized in that, By integrating the historical equivalent length and the real-time equivalent length, the comprehensive equivalent length of each line segment and the line adjacency matrix of the traffic road network are obtained, including: Based on the historical equivalent length of each route segment, combined with the real-time equivalent length of each route segment and each intersection, and according to the traffic topology of the road network, the comprehensive equivalent length of each route segment is obtained. By combining the combined equivalent lengths of each line segment at the same time, the line adjacency matrix of the traffic road network is obtained.

7. The electric vehicle path planning method based on multi-source data fusion according to claim 6, characterized in that, Based on the user-defined starting and ending points of the path, when obtaining the optimal path, the Dijkstra greedy algorithm is used to calculate the shortest path from the starting point to the ending point in the traffic road network based on the comprehensive equivalent length and the line adjacency matrix, and the shortest path is output as the optimal path.

8. The electric vehicle path planning method based on multi-source data fusion according to claim 7, characterized in that, The method employs Dijkstra's greedy algorithm to calculate the shortest path from the starting point to the ending point in the traffic road network, specifically: Label each intersection in the traffic road network and define the set of intersections with determined shortest paths and the set of intersections with undetermined shortest paths. Initialize the set of intersections, and initialize the starting point, all intersections except the starting point, and the current intersection; Iterate through the adjacent intersections connected to the current intersection, calculate the equivalent length of the new path and update the equivalent length of the original path, until the shortest path from the starting point to the ending point is obtained.

9. The electric vehicle path planning method based on multi-source data fusion according to claim 8, characterized in that, Iterate through the adjacent intersections connected to the current intersection, calculate the equivalent length of the new path, and update the equivalent length of the original path, including: Calculate the combined equivalent length between the current intersection and its adjacent intersections; Based on the equivalent path length from the starting point to the current intersection, calculate the equivalent path length from the starting point to the intersection adjacent to the current intersection. The equivalent length of the original path is compared with the equivalent length of the new path, and the equivalent length of the original path is updated to the minimum value between the equivalent length of the original path and the equivalent length of the new path.

10. The electric vehicle path planning method based on multi-source data fusion according to claim 8 or 9, characterized in that, When obtaining the shortest path from the starting point to the ending point The set of intersections with undetermined shortest paths is empty and / or the user-defined destination is added to the set of intersections with determined shortest paths.

Images