An edge-computing-based hydrogen energy vehicle intelligent scheduling system

Abstract

This invention relates to the field of intelligent scheduling technology for hydrogen fuel cell vehicles, and more particularly to an intelligent scheduling system for hydrogen fuel cell vehicles based on edge computing. The system includes an initial planning module, a data acquisition module, a modeling module, and a replanning module. The initial planning module calculates a first target operating speed and a first target operating route. The data acquisition module collects data and generates a constraint set. The modeling module establishes a multi-objective analysis model based on the constraints and analyzes whether the first target operating speed and the first target operating route meet the hydrogen consumption requirements. The replanning module replans a second target operating speed and a second target operating route for the target vehicle when the hydrogen consumption requirements are not met. This invention processes multi-dimensional constraint data in real time and dynamically generates speeds and paths through edge computing, achieving efficient, safe, and energy-saving scheduling of hydrogen fuel cell vehicles in extreme environments and closed paths, ensuring task feasibility and energy utilization efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent scheduling technology for hydrogen fuel cell vehicles, and in particular to an intelligent scheduling system for hydrogen fuel cell vehicles based on edge computing. Background Technology

[0002] Hydrogen energy, as a clean and efficient energy source, is being used more and more widely in the transportation sector.

[0003] Hydrogen-powered vehicles have advantages such as zero emissions, rapid refueling, and long driving range, and are widely used in public transportation, logistics, and special vehicle scenarios. As the fleet size expands, the operation scheduling, energy consumption management, and task allocation of hydrogen-powered vehicles have become key issues for system performance optimization.

[0004] Existing vehicle dispatching systems mostly rely on centralized computing, using cloud servers to aggregate data and issue operational instructions.

[0005] However, for hydrogen-powered vehicles, the hydrogen storage capacity is limited and energy consumption is highly sensitive to operating speed and route, making it difficult for traditional scheduling methods to complete real-time planning in a short period of time. At the same time, extreme environmental conditions such as high temperature, low temperature, strong wind, and strong ultraviolet radiation have a significant impact on vehicle performance and hydrogen consumption, increasing the requirements for real-time performance and accuracy of the scheduling system.

[0006] In driving scenarios with closed paths or fixed topologies, such as park transportation and mining area scheduling, vehicle scheduling not only needs to meet energy consumption and task completion requirements, but also needs to consider road segment characteristics. In such scenarios, edge computing technology can push data processing and scheduling optimization down to the vehicle end or roadside edge nodes, enabling real-time analysis and multi-objective decision-making of environmental data, vehicle status and road conditions.

[0007] Against this backdrop, intelligent scheduling of hydrogen-powered vehicles urgently requires a system capable of fully utilizing edge computing for real-time multi-objective analysis and dynamic path optimization under closed paths and extreme environmental conditions, in order to ensure that vehicles complete transportation tasks safely, efficiently, and energy-savingly.

[0008] Chinese Patent Publication No. CN114519551A discloses a scheduling method, device, and storage medium for hydrogen-powered freight vehicles. By fully scheduling hydrogen-powered freight vehicles and ordinary freight vehicles, the aim is to achieve wider use of hydrogen-powered freight vehicles. By conducting multi-dimensional evaluation of the scheme of using hydrogen-powered freight vehicles and ordinary freight vehicles in combination, an objective evaluation result is obtained. Finally, the target transportation scheme information is sent to the hydrogen-powered freight vehicles and ordinary freight vehicles in the target transportation scheme.

[0009] At the same time, existing intelligent scheduling technologies for hydrogen-powered vehicles mainly rely on centralized computing and static scheduling, which are difficult to cope with real-time changes in extreme environments. In particular, they are prone to delays or data loss when the route is closed or the local network is restricted. They also lack the ability to dynamically calculate and replan the remaining hydrogen storage capacity of vehicles and the hydrogen consumption of the route, which may lead to energy waste or scheduling failures in actual operation. Furthermore, they have significant shortcomings in the comprehensive analysis of environmental constraints, road gradients, and road condition changes. Summary of the Invention

[0010] To address this, the present invention provides an intelligent scheduling system for hydrogen-powered vehicles based on edge computing, which overcomes the problem of low efficiency in scheduling methods under extreme environments, closed paths, and limited network conditions in the prior art.

[0011] To achieve the above objectives, the present invention provides an intelligent scheduling system for hydrogen fuel cell vehicles based on edge computing, comprising:

[0012] The initial planning module is used to obtain historical scheduling data, including path-specific data and vehicle status data, within the historical scheduling period corresponding to the previous scheduling task. Based on the initial planning calculation function and the historical scheduling data, it calculates the first target running speed and the first target running route of each target vehicle after the current scheduling task is started.

[0013] The data acquisition module, connected to the initial planning module, is used to call historical scheduling data when the current scheduling task is started, and to collect initial scheduling data including environmental data and vehicle operation data. Based on the historical scheduling data and the initial scheduling data, it generates a set of constraints including a set of environmental constraints, a set of inherent path constraints, and a set of vehicle state constraints.

[0014] The modeling module, connected to the initial planning module and the data acquisition module, is used to establish a multi-objective analysis model based on the initial planning calculation function and the set of constraints, and to analyze whether the hydrogen consumption requirements are met under the first objective running speed and the first objective running route.

[0015] The replanning module, connected to the data acquisition module and the modeling module, is used to replan the second target running speed and second target running route of the target vehicle after the current scheduling task is started, based on the analysis results of the multi-objective analysis model when the hydrogen consumption requirements are not met.

[0016] Furthermore, the initial planning module includes a velocity initial planning unit;

[0017] The initial speed planning unit calculates the first target running speed based on the vehicle status data and path inherent data in the historical scheduling data through an initial speed calculation function.

[0018] Furthermore, the initial velocity planning unit includes a normalization calculation subunit, a factor calculation subunit, and a velocity calculation subunit;

[0019] The normalization calculation subunit is used to normalize the path-specific data and vehicle status data;

[0020] The factor calculation subunit is connected to the normalization calculation subunit and is used to calculate the path factor and vehicle factor of each path segment based on the normalization factor, through the path factor calculation function and the vehicle factor calculation function, respectively.

[0021] The speed calculation subunit is connected to the normalization calculation subunit and the factor calculation subunit to calculate the initial target speed of each path segment and summarize them to form the first target running speed set.

[0022] Furthermore, the initial planning module also includes a path initial planning unit;

[0023] The initial path planning unit, connected to the initial speed planning unit, is used to calculate the first target route based on the inherent path data and vehicle status data in the historical scheduling data through an initial path planning function.

[0024] Furthermore, the initial route planning unit includes a toll cost calculation subunit, a total cost accumulation subunit, and a route decision subunit;

[0025] The toll cost calculation subunit is used to calculate the toll cost of each path segment based on the normalized factors and the weights corresponding to each factor.

[0026] The total cost accumulation subunit is connected to the toll cost calculation subunit and is used to weight the toll cost according to the length of each path segment and calculate the weighted total path cost of all path segments.

[0027] The path decision subunit is connected to the total cost accumulation subunit and is used to compare the total path cost of each feasible path combination and select the combination with the minimum total path cost as the first target running route.

[0028] Furthermore, the data acquisition module includes an acquisition unit and a constraint generation unit;

[0029] The data acquisition unit is used to retrieve historical scheduling data when the current scheduling task is started, and to collect initial scheduling data, including environmental data and vehicle operation data.

[0030] The constraint generation unit, connected to the acquisition unit, is used to convert the environmental data, path-specific data, and vehicle status data in the historical scheduling data and the initial scheduling data into constraint sets including environmental constraint sets, path-specific constraint sets, vehicle operation constraint sets, and vehicle status constraint sets, respectively.

[0031] Furthermore, the modeling module includes a constraint parsing unit;

[0032] The constraint parsing unit is used to input the constraints from the environmental constraint set, path constraint combination, and vehicle state constraint set into the multi-objective analysis model.

[0033] Furthermore, the modeling module also includes a combined verification unit;

[0034] The combined verification unit, connected to the constraint parsing unit, is used to construct a speed-path matrix, calculate the ideal total hydrogen consumption corresponding to all elements in the matrix, and determine the comparison result between the ideal total hydrogen consumption and the vehicle's remaining hydrogen storage.

[0035] Furthermore, the combined verification unit includes a matrix construction subunit, an ideal hydrogen consumption calculation subunit, and a hydrogen quantity comparison subunit;

[0036] The matrix construction sub-unit is used to construct a speed-path matrix based on the running speed and route of the first target.

[0037] The ideal hydrogen consumption calculation subunit is connected to the matrix construction subunit and is used to calculate the ideal hydrogen consumption of each element in the matrix based on historical scheduling data and combined with gravitational acceleration and rolling resistance coefficient.

[0038] The hydrogen quantity comparison subunit is connected to the ideal hydrogen consumption calculation subunit. It is used to sum the ideal hydrogen consumption of each element in the matrix to obtain the ideal total hydrogen consumption, and compare the ideal total hydrogen consumption with the remaining hydrogen storage of the vehicle to obtain the hydrogen quantity comparison result.

[0039] Furthermore, the replanning module includes a speed re-correction unit and a path re-optimization unit;

[0040] The speed correction unit is used to correct the first target route based on the hydrogen quantity comparison result to obtain the second target route;

[0041] The path re-optimization unit is used to obtain the second target running speed corresponding to the second target running route when the second target running route is obtained.

[0042] Compared with existing technologies, the advantages of this invention are as follows: by acquiring historical scheduling information, environmental information, and vehicle status information in real time, and combining multi-dimensional constraints to dynamically optimize vehicle speed and route, intelligent scheduling of hydrogen-powered vehicles in closed paths and extreme environments is achieved; the system can automatically correct the running speed and optimize the route when hydrogen consumption is insufficient, ensuring that the vehicle safely reaches the target while maximizing the utilization of remaining hydrogen storage; the application of edge computing enables distributed real-time decision-making, significantly reducing scheduling latency and improving scheduling accuracy and energy utilization efficiency; in addition, this invention can adapt to complex road condition changes and task execution under extreme environmental conditions, overcoming the limitations of existing technologies such as inaccurate scheduling, slow response speed, and insufficient hydrogen consumption control in closed environments, providing reliable technical support for the safe and efficient operation of hydrogen-powered vehicles.

[0043] Furthermore, by introducing an initial speed calculation function driven by historical data, the preliminary target speed of each path segment can be quickly generated through edge computing, improving the scheduling response speed. This unit effectively combines path and vehicle state factors to ensure the rationality and adaptability of speed planning, providing a basis for calculation and analysis for subsequent hydrogen consumption analysis.

[0044] Furthermore, by unifying multidimensional parameters into normalized factors and performing hierarchical calculations of path factors and vehicle factors, sensitive control of speed planning is achieved. The resulting initial target speed set for each segment can more realistically reflect the road environment and vehicle performance characteristics, thereby improving the accuracy and stability of hydrogen energy vehicle scheduling path planning. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the structure of the intelligent dispatching system for hydrogen fuel cell vehicles based on edge computing, according to an embodiment of the present invention.

[0046] Figure 2 This is a schematic diagram of the initial planning module in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the modeling module in an embodiment of the present invention;

[0048] Figure 4 This is a logic decision diagram of the hydrogen quantity comparison subunit in an embodiment of the present invention. Detailed Implementation

[0049] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0050] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0051] It should be noted that in the description of this invention, the terms "upper," "lower," "left," "right," "inner," and "outer," etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is merely for ease of description and does not indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0052] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0053] Please see Figure 1 The diagram shown is a structural schematic of an intelligent scheduling system for hydrogen fuel cell vehicles based on edge computing, according to an embodiment of the present invention. The present invention provides an intelligent scheduling system for hydrogen fuel cell vehicles based on edge computing, comprising:

[0054] The initial planning module is used to obtain historical scheduling data, including path-specific data and vehicle status data, within the historical scheduling period corresponding to the previous scheduling task. Based on the initial planning calculation function and the historical scheduling data, it calculates the first target running speed and the first target running route of each target vehicle after the current scheduling task is started.

[0055] The data acquisition module, connected to the initial planning module, is used to call historical scheduling data when the current scheduling task is started, and to collect initial scheduling data including environmental data and vehicle operation data. Based on the historical scheduling data and the initial scheduling data, it generates a set of constraints including a set of environmental constraints, a set of inherent path constraints, and a set of vehicle state constraints.

[0056] The modeling module, connected to the initial planning module and the data acquisition module, is used to establish a multi-objective analysis model based on the initial planning calculation function and the set of constraints, and to analyze whether the hydrogen consumption requirements are met under the first objective running speed and the first objective running route.

[0057] The replanning module, connected to the data acquisition module and the modeling module, is used to replan the second target running speed and second target running route of the target vehicle after the current scheduling task is started, based on the analysis results of the multi-objective analysis model when the hydrogen consumption requirements are not met.

[0058] In this embodiment, the historical scheduling data comes from the median statistical value collected and processed by the system in the previous scheduling cycle;

[0059] The start time of this scheduled task is defined as the starting point of the current scheduling cycle;

[0060] Within the current scheduling cycle, the first target running speed and the first target running route of each target vehicle are automatically calculated and generated by the system based on historical scheduling data through the initial planning calculation function. The initial planning calculation function includes an initial speed calculation function for calculating speed and an initial path planning function for calculating path. This process does not require manual intervention.

[0061] A multi-objective analysis model whose output is a non-fixed value within a certain range.

[0062] By acquiring historical scheduling information, environmental information, and vehicle status information in real time, and combining multi-dimensional constraints to dynamically optimize vehicle speed and route, intelligent scheduling of hydrogen-powered vehicles in closed paths and extreme environments is achieved. The system can automatically correct the running speed and optimize the route when hydrogen consumption is insufficient, ensuring that the vehicle safely reaches the target while maximizing the use of remaining hydrogen storage. The application of edge computing enables distributed real-time decision-making, significantly reducing scheduling latency and improving scheduling accuracy and energy utilization efficiency. In addition, this invention can adapt to complex road condition changes and task execution under extreme environmental conditions, overcoming the limitations of existing technologies such as inaccurate scheduling, slow response speed, and insufficient hydrogen consumption control in closed environments, providing reliable technical support for the safe and efficient operation of hydrogen-powered vehicles.

[0063] See Figure 2 As shown, it is a structural schematic diagram of the initial planning module in an embodiment of the present invention;

[0064] Specifically, the initial planning module includes a velocity initial planning unit;

[0065] The initial speed planning unit calculates the first target running speed based on the vehicle status data and path inherent data in the historical scheduling data through an initial speed calculation function.

[0066] By introducing an initial speed calculation function driven by historical data, the preliminary target speed of each path segment can be quickly generated through edge computing, improving the scheduling response speed. This unit effectively combines path and vehicle state factors to ensure the rationality and adaptability of speed planning, providing a basis for calculation and analysis for subsequent hydrogen consumption analysis.

[0067] Specifically, the initial velocity planning unit includes a normalization calculation subunit, a factor calculation subunit, and a velocity calculation subunit;

[0068] The normalization calculation subunit is used to normalize the path-specific data and vehicle status data;

[0069] The factor calculation subunit is connected to the normalization calculation subunit and is used to calculate the path factor and vehicle factor of each path segment based on the normalization factor, through the path factor calculation function and the vehicle factor calculation function, respectively.

[0070] The speed calculation subunit is connected to the normalization calculation subunit and the factor calculation subunit to calculate the initial target speed of each path segment and summarize them to form the first target running speed set.

[0071] In this embodiment, the planned path is only from point A to point B for hydrogen-powered vehicles, and the path traveled by the hydrogen-powered vehicles is a closed road segment with a fixed topology.

[0072] The path from starting point A to ending point B consists of four connected segments in the order of travel, including:

[0073] Path segment 1: A straight, slope-free section of road with a length of L1 and a starting curvature of k1 = 0;

[0074] Path segment 2: A section of road with no slope and a bend, with a length of L2. The curvature k2 of this section is reflected at the connection between path 1 and path 2, and this connection is a right-angle bend.

[0075] Path segment 3: Uphill straight section with a slope of g3 and a length of L3. The connection between path 2 and path 3 is a right-angle bend with a curvature of k3.

[0076] Path segment 4: Uphill straight section with a slope of g4 and a length of L4. The connection between path 3 and path 4 is a right angle with a curvature of k4.

[0077] Among them, the connection points of each path segment are all right-angle bends. The curvature of path segment 1 is the starting point of path segment 1. The curvature of path segments 2, 3, and 4 is the connection point between the starting point of this path segment and the ending point of the previous path point.

[0078] Each path segment includes inherent path data such as historical slope g, historical curvature k, historical pothole density D, and historical length L. This inherent path data is obtained from the inspection of closed road sections by manual maintenance of high-precision maps.

[0079] Retrieve from historical scheduling data including path segment reference slope g ref Path segment reference curvature k ref Path reference pothole density D ref Vehicle reference mass M ref Rated drive power P ref Reference maximum hydrogen storage capacity H ref Segment reference speed The reference constants are all derived from historical statistics;

[0080] The median of the actual speeds collected on the i-th segment during the historical scheduling period;

[0081] Normalization calculation is performed for each segment i∈{1,2,3,4}:

[0082]

[0083] Where, p g,i p is the normalized slope of the first path segment of segment i; k,i p is the normalization factor for the curvature of the path segment after normalization. D,i p is the normalization factor for the pothole density of the normalized path segment; M p is the normalization factor for the vehicle's overall mass after normalization. H p is the normalization factor for the maximum hydrogen storage capacity of the vehicle after normalization. P g is the normalization factor for the rated drive power after normalization. ref The values ​​are calculated based on the road design drawings and range from [0, 0.1]. The one-way closed road section from point A to point B only includes straight sections and uphill sections. Preferably, the uphill section is 0.05 and the flat section is 0.

[0084] k ref The value is obtained from the road's geometric radius, ranging from [0.01, 0.05] 1 / m, preferably 0.05;

[0085] D ref The data was obtained through road inspection statistics, with a range of [0, 10] items / km, preferably 7 items / km.

[0086] M refBased on the fleet sample statistics, the values ​​vary slightly for different vehicle models, ranging from [1000, 3500] kg, with 2000 kg being the preferred value.

[0087] P ref The power is derived from the vehicle's powertrain nameplate parameters. The power varies for different models, with a range of [80, 200] kW. Preferably, 100 kW is used.

[0088] H ref The hydrogen tank volume is determined by the vehicle design specifications, and the value ranges from [5, 10] kg, preferably 6 kg.

[0089] The path factor and vehicle factor are calculated using the following formulas:

[0090]

[0091] in, To set a lower bound for the path factor, and to avoid reducing the running speed of the first target to zero due to extreme values, we take... It is 0.2;

[0092] This is the upper limit of the path factor to avoid extreme values ​​causing the running speed of the first target to deviate from reality.

[0093] in, In order to convert 1+b1(1-p) M )+b2(p P -1)+b3(p H -1) Limited to the interval middle;

[0094] a1 is the sensitivity coefficient of the path segment slope, used to characterize the degree to which changes in the path segment slope restrict the target operating speed planning; a2 is the sensitivity coefficient of the path segment curvature, used to characterize the degree to which the path segment curvature restricts the target operating speed planning; a3 is the sensitivity coefficient of the path segment pothole density, used to characterize the degree to which the path pothole density restricts the target operating speed planning; the larger the sensitivity coefficient, the stronger the speed suppression.

[0095] In this embodiment, a1∈[0.3,1.0], with a preferred value of 0.6; a2∈[0.2,0.8], with a preferred value of 0.4; a3∈[0.1,0.5], with a preferred value of 0.2;

[0096] b1 is the sensitivity coefficient of the vehicle's total mass, used to characterize the degree to which the vehicle's total mass restricts the target operating speed planning; b2 is the sensitivity coefficient of the rated drive power, used to characterize the degree to which the rated drive power restricts the target operating speed planning; b3 is the sensitivity coefficient of the vehicle's maximum hydrogen storage capacity, used to characterize the degree to which the vehicle's maximum hydrogen storage capacity restricts the target operating speed planning.

[0097] In this embodiment, b1∈[0.05, 0.3], with a preferred value of 0.1; b2∈[0.1, 0.5], with a preferred value of 0.2; b3∈[0.01, 0.2], with a preferred value of 0.1;

[0098] The formula for calculating the initial target velocity of a segment is:

[0099]

[0100] The first target running speed is the set of the initial target speeds of the four path segments from A to B;

[0101]

[0102] Each It is the initial target speed of segment i calculated based on historical scheduling data.

[0103] By unifying multidimensional parameters into normalized factors and performing hierarchical calculations of path factors and vehicle factors, sensitive control of speed planning is achieved. The resulting initial target speed set for each segment can more realistically reflect the road environment and vehicle performance characteristics, thereby improving the accuracy and stability of hydrogen energy vehicle scheduling path planning.

[0104] Specifically, the initial planning module further includes a path initial planning unit;

[0105] The initial path planning unit, connected to the initial speed planning unit, is used to calculate the first target route based on the inherent path data and vehicle status data in the historical scheduling data through an initial path planning function.

[0106] Specifically, the initial route planning unit includes a toll cost calculation subunit, a total cost accumulation subunit, and a route decision subunit;

[0107] The toll cost calculation subunit is used to calculate the toll cost of each path segment based on the normalized factors and the weights corresponding to each factor.

[0108] The total cost accumulation subunit is connected to the toll cost calculation subunit and is used to weight the toll cost according to the length of each path segment and calculate the weighted total path cost of all path segments.

[0109] The path decision subunit is connected to the total cost accumulation subunit and is used to compare the total path cost of each feasible path combination and select the combination with the minimum total path cost as the first target running route.

[0110] In this embodiment, the travel cost of each path segment is calculated:

[0111] A i =w g ·p g,i +w k ·p k,i +w D ·p D,i +w M ·p M +w P ·p P +w H ·p H

[0112] Among them, w g The slope weight of the path segment is obtained by fitting vehicle energy consumption under different slope intervals in historical data; the value range is [0.15, 0.25], and preferably 0.2;

[0113] w k The curvature weight of the path segment is obtained by fitting the combined effects of vehicle steering safety and speed loss under different curvature radii; the value range is [0.10, 0.20], and preferably 0.15;

[0114] w D The pothole density weight is obtained by fitting the effect of road smoothness on vehicle vibration and hydrogen consumption stability; the value range is [0.05, 0.15], preferably 0.1;

[0115] w M The weight of the vehicle's total mass is obtained by fitting the influence of the vehicle's total mass on the power output demand and uphill energy consumption; the value range is [0.10, 0.20], and preferably 0.15;

[0116] w P The rated drive power weight is obtained by fitting the effect of the vehicle's rated drive power attenuation characteristics on climbing ability and stability in high load range; the value range is [0.15, 0.25], preferably 0.20;

[0117] w H The maximum hydrogen storage capacity of the vehicle is the weight, which is obtained by fitting the influence of the vehicle's rated drive power decay characteristics on the climbing ability and stability in the high load range. The value range is [0.15, 0.25], and preferably 0.20.

[0118] At the same time, ∑(wg +w k +w D +w M +w P +w H ) = 1;

[0119] After the toll cost for each segment is calculated, the initial route planning unit uses a segmented cumulative approach to calculate the total route cost:

[0120]

[0121] According to A total The principle of minimization is used to determine the vehicle's first target route, and the output is a set of segmented paths {Path1, Path2, Path3, Path4}, where each sub-path corresponds to the calculated optimal path segment.

[0122] By weighting the normalized path factors and vehicle factors into a model, segmented travel costs are formed and accumulated into the total path cost. Then, based on the principle of minimization, the optimal path combination is selected, which effectively avoids planning deviations caused by a single factor and optimizes energy consumption, stability and safety in path and speed planning.

[0123] Specifically, the data acquisition module includes an acquisition unit and a constraint generation unit;

[0124] The data acquisition unit is used to retrieve historical scheduling data when the current scheduling task is started, and to collect initial scheduling data, including environmental data and vehicle operation data.

[0125] The constraint generation unit, connected to the acquisition unit, is used to convert the environmental data, path-specific data, and vehicle status data in the historical scheduling data and the initial scheduling data into constraint sets including environmental constraint sets, path-specific constraint sets, vehicle operation constraint sets, and vehicle status constraint sets, respectively.

[0126] In this embodiment, the acquisition unit retrieves historical operation records through the task management system and obtains vehicle status data (H) after data preprocessing. max (M, P, N) and path-specific data (g) i ,k i D i ,L i );

[0127] Data is collected through onboard sensors and environmental monitoring equipment, including ambient temperature T obtained by a temperature sensor. env Wind speed sensor acquires ambient wind speed V wind And the ambient ultraviolet intensity U obtained by the ultraviolet sensor env ;

[0128] The set of environmental constraints is:

[0129] C env ={C T C U C V}

[0130] Among them, C T Due to environmental temperature constraints, C U To constrain environmental ultraviolet radiation, C V Environmental wind speed constraints;

[0131] The set of environmental constraints is limited to interval form, i.e., C. env ={T min ≤C T ≤T max U min ≤C U ≤U max V min ≤C V ≤V max};

[0132] T min = -30℃, T max +40℃ is the boundary of the extreme measurable ambient temperature operating condition.

[0133] U min =0, U max =12UV index, which represents the boundary of the extreme measurable ambient UV intensity operating condition;

[0134] V min =0, V max =15m / s, which is the boundary condition for the extreme measurable environmental wind speed;

[0135] Path inherent constraint set:

[0136] C path ={C g C k C D C L}

[0137] Among them, C g For the slope constraint of the path segment, C k For path segment curvature constraints, C D Constraints on pothole density for path segments;

[0138] The set of inherent constraints of the path is limited to interval form, that is:

[0139] C path ={g min ≤Cg ≤g max ,k min ≤C k ≤k max D min ≤C D ≤D max ,L min ≤L i

[0140] ≤L max}

[0141] g min =0, g max =0.1, which is the measurable slope of the road segment within the closed road section;

[0142] k min =0,k max =0.05m -1 0.1m -1 For a turn with a radius of 20m, the curvature of the path segment that can be measured within the closed road section is given.

[0143] D min =0,D max =20 potholes / km; This represents the measurable pothole density within a closed road section.

[0144] L min =0,L max =5km;

[0145] Vehicle state constraint set:

[0146] C veh ={C H C M C P C N}

[0147] Where C H The maximum hydrogen storage capacity of the vehicle is constrained; C M For the overall vehicle weight constraint; C P The vehicle's rated drive power is constrained; C N To constrain the number of vehicle maintenance operations, data is uploaded and stored in real time via sensors and edge nodes.

[0148] The vehicle state constraint set is limited to interval form, that is:

[0149]

[0150] in,

[0151] M min =1000kg,Mmax =3500kg;

[0152] P min =80kW,P max =200kW,

[0153] N min =0,N max =200;

[0154] The vehicle's operational constraints are obtained, and the remaining hydrogen storage capacity (H) is collected by several sensors installed both externally and internally on the vehicle. remain ;

[0155] C run ={H remain}

[0156] By simultaneously calling historical scheduling data and real-time sensor data when the scheduling task is started, multi-dimensional parameters are uniformly transformed into a multi-dimensional constraint set. Furthermore, by combining vehicle status parameters and remaining hydrogen storage capacity, an operational constraint set is generated, enabling the scheduling system to express all-round constraints on environmental conditions, road conditions, and vehicle performance, effectively ensuring the rationality of the planning calculation boundary.

[0157] See Figure 3 As shown, it is a logic decision diagram of the modeling module in an embodiment of the present invention;

[0158] Specifically, the modeling module includes a constraint parsing unit;

[0159] The constraint parsing unit is used to input the constraints from the environmental constraint set, path constraint combination, and vehicle state constraint set into the multi-objective analysis model.

[0160] In this embodiment, the constraint parsing unit receives a constraint set generated by the data acquisition module, including: an environmental constraint set C. env Path inherent constraint set C path Vehicle state constraint set C veh and the vehicle operation constraint set C run ;

[0161] C total =C env ∪C path ∪C veh ∪C run

[0162] and C total Input a multi-objective analysis model.

[0163] By uniformly analyzing and inputting environmental constraints, path-specific constraints, vehicle state constraints, and vehicle operation constraints into a multi-objective analysis model, and assigning differentiated weights to different constraints during the analysis process, a comprehensive balance is achieved for multi-dimensional objectives such as energy consumption, safety, and stability. This enables the scheduling model to have flexible adaptability and dynamic adjustment capabilities.

[0164] Specifically, the modeling module also includes a combined verification unit;

[0165] The combined verification unit, connected to the constraint parsing unit, is used to construct a speed-path matrix, calculate the ideal total hydrogen consumption corresponding to all elements in the matrix, and determine the comparison result between the ideal total hydrogen consumption and the vehicle's remaining hydrogen storage.

[0166] See Figure 4 As shown, it is the logic decision diagram of the hydrogen quantity comparison subunit in an embodiment of the present invention;

[0167] Specifically, the combined verification unit includes a matrix construction subunit, an ideal hydrogen consumption calculation subunit, and a hydrogen quantity comparison subunit;

[0168] The matrix construction sub-unit is used to construct a speed-path matrix based on the running speed and route of the first target.

[0169] The ideal hydrogen consumption calculation subunit is connected to the matrix construction subunit and is used to calculate the ideal hydrogen consumption of each element in the matrix based on historical scheduling data and combined with gravitational acceleration and rolling resistance coefficient.

[0170] The hydrogen quantity comparison subunit is connected to the ideal hydrogen consumption calculation subunit. It is used to sum the ideal hydrogen consumption of each element in the matrix to obtain the ideal total hydrogen consumption, and compare the ideal total hydrogen consumption with the remaining hydrogen storage of the vehicle to obtain the hydrogen quantity comparison result.

[0171] In this embodiment, based on the first target running speed Construct a speed-path combination matrix with the first target's running route {Path1, Path2, Path3, Path4}. Each element in the matrix corresponds to a velocity-path combination;

[0172] The ideal hydrogen consumption of each element in the matrix is ​​calculated based on the path segment length, path segment slope, path segment curvature, vehicle mass, and path segment pothole density from historical scheduling data.

[0173] The calculation formula is:

[0174]

[0175] For vehicles at speed via path segment i Ideal hydrogen consumption;

[0176] F traction This refers to traction force, measured in N.

[0177] L i This represents the length of the path segment.

[0178] H energy\_per\_unit The unit of hydrogen energy represents the power output that can be provided by consuming 1 kg of hydrogen, and the unit is J / kg. It is related to the vehicle model. In this embodiment, it is taken as 60 MJ / kg.

[0179] The traction force is:

[0180] F traction =M·g·(sing i +f rolling )+F cornering

[0181] Among them, g i Let g be the slope of the path segment, and g be the acceleration due to gravity.

[0182] f rolling This is the rolling resistance coefficient, which is related to the material of the path segment; in this embodiment, it is taken as 0.4.

[0183] F cornering The turning resistance is the ratio of the vehicle's total mass to its weight. The product of the square and the curvature of the path segment;

[0184] The ideal total hydrogen consumption is obtained by summing the ideal hydrogen consumption of each element in the matrix and comparing it with the remaining hydrogen storage of the vehicle. If the ideal total hydrogen consumption is greater than the remaining hydrogen storage of the vehicle, the first hydrogen consumption comparison result is obtained, and the first target operating speed and the first target operating route do not meet the hydrogen consumption requirements.

[0185] If the ideal total hydrogen consumption is less than or equal to the vehicle's remaining hydrogen storage, a second hydrogen quantity comparison result is obtained. If the first target operating speed and the first target operating route meet the hydrogen consumption requirements, the first target operating speed and the first target operating route will be used as the actual scheduling operating speed and the actual scheduling operating route for this scheduling task.

[0186] The system quantitatively estimates energy consumption levels under different operating speeds and route combinations; then, by comparing this with the remaining hydrogen storage capacity of the vehicles, it effectively avoids mid-journey failures caused by insufficient hydrogen energy during the execution of the dispatching plan, thereby improving the feasibility and energy utilization efficiency of hydrogen vehicle dispatching tasks.

[0187] Specifically, the replanning module includes a speed re-correction unit and a path re-optimization unit;

[0188] The speed correction unit is used to correct the first target route based on the hydrogen quantity comparison result to obtain the second target route;

[0189] The path re-optimization unit is used to obtain the second target running speed corresponding to the second target running route when the second target running route is obtained.

[0190] In this embodiment, the replanning module is activated when it receives the first hydrogen quantity comparison result from the modeling module, i.e., when it is determined that the first target running speed and route may lead to insufficient hydrogen quantity. At the same time, the remaining hydrogen storage of the vehicle is sufficient to complete the entire one-way scheduling task from the starting point A to the destination B. Any vehicle that does not meet this basic passage requirement will be directly excluded by the system after the current scheduling task is started and will not participate in the current scheduling task.

[0191] The system obtains the hydrogen quantity comparison results within the matrix and obtains the path segment in the first target running route corresponding to the element of the first hydrogen quantity comparison result. Based on the multi-objective analysis model, it generates a set of candidate running routes that avoid the path segment and calculates the ideal total hydrogen consumption of each candidate running route.

[0192] From the candidate routes whose ideal total hydrogen consumption does not exceed the vehicle's remaining hydrogen storage capacity, the route with the minimum ideal total hydrogen consumption is selected as the second target route.

[0193] The speed re-correction unit recalculates the running speed of each path segment based on the second target running route and the inherent path data of each path segment to obtain the second target running speed, and uses the second target running speed as the actual scheduling running speed and the second target running route as the actual scheduling running route.

[0194] Candidate routes are generated by a multi-objective analysis model, and the path combination with the minimum ideal hydrogen consumption is selected. Then, the operating speed of each segment is recalculated by combining the inherent data of the path to obtain the speed and route combination that meets the requirements of the remaining hydrogen storage capacity. This ensures that the scheduling scheme can still complete the entire transportation task under hydrogen energy constraints and improves the fault tolerance of the scheduling.

[0195] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0196] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A hydrogen fuel cell vehicle intelligent scheduling system based on edge computing, characterized in that, include: The initial planning module is used to obtain historical scheduling data, including path-specific data and vehicle status data, within the historical scheduling period corresponding to the previous scheduling task. Based on the initial planning calculation function and the historical scheduling data, it calculates the first target running speed and the first target running route of each target vehicle after the current scheduling task is started. The data acquisition module, connected to the initial planning module, is used to call historical scheduling data when the current scheduling task is started, and to collect initial scheduling data including environmental data and vehicle operation data. Based on the historical scheduling data and the initial scheduling data, it generates a set of constraints including a set of environmental constraints, a set of inherent path constraints, and a set of vehicle state constraints. The modeling module, connected to the initial planning module and the data acquisition module, is used to establish a multi-objective analysis model based on the initial planning calculation function and the set of constraints, and to analyze whether the hydrogen consumption requirements are met under the first objective running speed and the first objective running route. The replanning module, connected to the data acquisition module and the modeling module, is used to replan the second target running speed and second target running route of the target vehicle after the current scheduling task is started, based on the analysis results of the multi-objective analysis model when the hydrogen consumption requirements are not met. The initial planning module includes a velocity initial planning unit; The initial speed planning unit calculates the first target running speed based on the vehicle status data and path-specific data in the historical scheduling data through an initial speed calculation function. The initial velocity planning unit includes a normalization calculation subunit, a factor calculation subunit, and a velocity calculation subunit; The normalization calculation subunit is used to normalize the path-specific data and vehicle status data; The factor calculation subunit is connected to the normalization calculation subunit and is used to calculate the path factor and vehicle factor of each path segment based on the normalization factor, through the path factor calculation function and the vehicle factor calculation function, respectively. The speed calculation subunit is connected to the normalization calculation subunit and the factor calculation subunit to calculate the initial target speed of each path segment and summarize them to form the first target running speed set. The modeling module also includes a combined verification unit; The combined verification unit, connected to the constraint parsing unit, is used to construct a speed-path matrix, calculate the ideal total hydrogen consumption corresponding to all elements in the matrix, and determine the comparison result between the ideal total hydrogen consumption and the vehicle's remaining hydrogen storage. The combined verification unit includes a matrix construction subunit, an ideal hydrogen consumption calculation subunit, and a hydrogen quantity comparison subunit; The matrix construction sub-unit is used to construct a speed-path matrix based on the running speed and route of the first target. The ideal hydrogen consumption calculation subunit is connected to the matrix construction subunit and is used to calculate the ideal hydrogen consumption of each element in the matrix based on historical scheduling data and combined with gravitational acceleration and rolling resistance coefficient. The hydrogen quantity comparison subunit is connected to the ideal hydrogen consumption calculation subunit. It is used to sum the ideal hydrogen consumption of each element in the matrix to obtain the ideal total hydrogen consumption, and compare the ideal total hydrogen consumption with the remaining hydrogen storage of the vehicle to obtain the hydrogen quantity comparison result.

2. The intelligent dispatching system for hydrogen fuel cell vehicles based on edge computing according to claim 1, characterized in that, The initial planning module also includes a path initial planning unit; The initial path planning unit, connected to the initial speed planning unit, is used to calculate the first target route based on the inherent path data and vehicle status data in the historical scheduling data through an initial path planning function.

3. The intelligent dispatching system for hydrogen fuel cell vehicles based on edge computing according to claim 1, characterized in that, The initial route planning unit includes a toll cost calculation subunit, a total cost accumulation subunit, and a route decision subunit; The toll cost calculation subunit is used to calculate the toll cost of each path segment based on the normalized factors and the weights corresponding to each factor. The total cost accumulation subunit is connected to the toll cost calculation subunit and is used to weight the toll cost according to the length of each path segment and calculate the weighted total path cost of all path segments. The path decision subunit is connected to the total cost accumulation subunit and is used to compare the total path cost of each feasible path combination and select the combination with the minimum total path cost as the first target running route.

4. The intelligent dispatching system for hydrogen fuel cell vehicles based on edge computing according to claim 1, characterized in that, The data acquisition module includes an acquisition unit and a constraint generation unit; The data acquisition unit is used to retrieve historical scheduling data when the current scheduling task is started, and to collect initial scheduling data, including environmental data and vehicle operation data. The constraint generation unit, connected to the acquisition unit, is used to convert the environmental data, path-specific data, and vehicle status data in the historical scheduling data and the initial scheduling data into constraint sets including environmental constraint sets, path-specific constraint sets, vehicle operation constraint sets, and vehicle status constraint sets, respectively.

5. The intelligent dispatching system for hydrogen fuel cell vehicles based on edge computing according to claim 1, characterized in that, The modeling module includes a constraint parsing unit; The constraint parsing unit is used to input the constraints from the environmental constraint set, path constraint combination, and vehicle state constraint set into the multi-objective analysis model.

6. The intelligent dispatching system for hydrogen fuel cell vehicles based on edge computing according to claim 1, characterized in that, The replanning module includes a speed re-correction unit and a path re-optimization unit; The speed correction unit is used to correct the first target route based on the hydrogen quantity comparison result to obtain the second target route; The path re-optimization unit is used to obtain the second target running speed corresponding to the second target running route when the second target running route is obtained.

Images