A method, device and equipment for generating a collaborative replenishment sequence of a hybrid energy vehicle fleet

Abstract

The embodiment of the application provides a kind of mixed energy vehicle fleet's collaborative replenishment sequence generation method, it is applicable to port, logistics and mine scene etc..The method is by obtaining the replenishment demand information of each vehicle of vehicle fleet, especially the required replenishment time, vehicle is divided into long-time replenishment vehicle and short-time replenishment vehicle;And by generating first replenishment sequence for long-time replenishment vehicle and assigning fixed time window in priority;In the idle gap formed in the time window occupied by long-time replenishment vehicle, the second replenishment sequence of short-time replenishment vehicle is dynamically inserted.The method can significantly reduce the total waiting time of vehicle fleet at replenishment point, effectively solve the "barrel effect" caused by heterogeneous energy replenishment time, so as to improve mixed formation operation efficiency and resource utilization.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method, apparatus and device for generating a coordinated resupply sequence for a hybrid energy vehicle fleet. Background Technology

[0002] With the popularization of new energy vehicles, the logistics and transportation sector is gradually forming a hybrid energy fleet that includes electric, hydrogen fuel cell, and gasoline vehicles. However, the refueling time for each type of vehicle varies significantly. Charging electric vehicles takes much longer than refueling gasoline vehicles, which can easily lead to low overall efficiency when a few vehicles take too long to refuel, resulting in the "barrel effect".

[0003] Existing vehicle routing schemes primarily optimize individual vehicles, aiming to minimize travel time or energy consumption. Even when considering resupply factors, they only select the optimal resupply station for each vehicle, lacking a collaborative planning perspective that considers the overall operational efficiency of the fleet. This localized optimization of individual vehicles often leads to a loss of overall fleet operational efficiency. Summary of the Invention

[0004] This application provides a method for generating a collaborative resupply sequence for a hybrid energy vehicle fleet, which can significantly reduce the total waiting time of the fleet at resupply points, effectively solve the "barrel effect" caused by the heterogeneity of energy resupply time, and thus improve the operational efficiency and resource utilization of hybrid fleets.

[0005] In a first aspect, embodiments of this application provide a method for generating a coordinated resupply sequence for a hybrid energy vehicle fleet, including: Obtain the resupply requirement information of each vehicle in the convoy. The resupply requirement information includes at least the required resupply time. The required resupply time is used to divide the vehicles in the convoy into long-term resupply vehicles and short-term resupply vehicles. A first supply sequence is generated for the long-term supply vehicle, and a corresponding first supply time window is allocated to the long-term supply vehicle; Within one or more time gaps formed by the first replenishment time window, a second replenishment sequence is dynamically inserted for the short-term replenishment vehicle, and a corresponding second replenishment time window is allocated; A coordinated resupply sequence for the convoy is generated based on the first resupply sequence and the second resupply sequence.

[0006] In this embodiment, by prioritizing resource allocation for vehicles with longer refueling times and establishing fixed time windows, parallel refueling opportunities are created for vehicles with shorter refueling times. This optimizes the originally sequential and dispersed refueling process into a highly parallel collaborative process. It significantly reduces the total waiting time and total task time of the fleet at refueling points, effectively addressing the "weakest link" effect caused by the heterogeneity of energy refueling times, and improving the overall operational efficiency and resource utilization of the hybrid energy fleet.

[0007] In one possible implementation, allocating a corresponding first resupply time window for the long-term resupply vehicle includes: calculating a target resupply station for the long-term resupply vehicle based on the real-time status information of the resupply station; calculating a target resupply start time with the goal of minimizing the total waiting time of the long-term resupply vehicle; and generating the first resupply time window based on the target resupply station, the target resupply start time, and the resupply time required by the vehicle.

[0008] In this embodiment of the application, by intelligently matching target supply stations and planning the optimal supply time window for long-term supply vehicles, the uncertain queuing and waiting is transformed into deterministic planning, eliminating the main delay in the fleet supply process from the source and providing an opportunity for the parallel insertion of subsequent short-term vehicles.

[0009] In one possible implementation, dynamically inserting the second supply sequence for the short-term supply vehicle includes: identifying the idle time gaps between all the first supply time windows, and matching the supply task of the short-term supply vehicle with the idle time gaps. The matching constraints include: the supply time of the short-term supply vehicle is less than or equal to the duration of the idle time gap, and the short-term supply vehicle is spatially capable of reaching and utilizing the supply station corresponding to the idle time gap; obtaining the optimal matching scheme that satisfies the constraints, and generating the second supply sequence.

[0010] In this embodiment, by precisely embedding short-term resupply tasks into the idle time window formed by long-term resupply, a fundamental shift from serial waiting to parallel collaboration in the fleet resupply process is achieved. This fully leverages the time fragment resources in task scheduling, enabling short-term vehicles to complete resupply without affecting the critical path, thereby minimizing the fleet's ineffective waiting time and significantly improving overall operational efficiency and resource utilization.

[0011] In one possible implementation, the generation and adjustment of the coordinated supply sequence are performed under a distributed architecture, including: each vehicle or vehicle group in the fleet acts as a distributed node, and the nodes exchange their respective supply plans through vehicle-to-everything (V2X) communication; when any node detects a deviation from the supply plan, it triggers a local replanning, and a distributed consensus algorithm is used to converge the local plans of each node to a new globally optimal or near-optimal target coordinated supply sequence.

[0012] In this embodiment, a distributed architecture decomposes the centralized planning task into parallel processing across vehicle nodes. When a single node deviates from its plan, the system can quickly reach a new globally optimal solution through local replanning and distributed negotiation, achieving a leap from static planning to dynamic adaptation in fleet resupply scheduling. The decentralized collaboration mechanism significantly improves the system's response speed and robustness to emergencies, ensuring that the hybrid energy fleet maintains efficient collaborative resupply capabilities in dynamically changing environments.

[0013] In one possible implementation, the resupply requirement further includes one or more of the following: vehicle remaining energy, energy consumption rate, destination information, vehicle maximum energy capacity, and resupply rate.

[0014] In this embodiment, a refined vehicle energy profile is constructed by introducing multi-dimensional replenishment demand parameters. This means the system can quantitatively assess the urgency and feasibility of vehicle replenishment based on accurate energy situational awareness, thereby formulating a replenishment plan that meets both energy security boundaries and optimal operational efficiency, significantly improving the accuracy and reliability of replenishment sequence planning.

[0015] In one possible implementation, the method further includes: dynamically determining thresholds for the long-term supply vehicles and the short-term supply vehicles based on the median, average, or cluster analysis of the vehicle resupply times in the fleet.

[0016] In this embodiment, a dynamic threshold division mechanism is used to enable vehicle classification to adapt to the actual composition and task characteristics of a specific fleet, avoiding the mismatch problem that may be caused by a fixed threshold. This ensures that the collaborative scheduling strategy of "long vehicles in fixed windows and short vehicles in gaps" always maintains optimal matching with the real-time status of the fleet, thereby maximizing the generation efficiency and execution effect of the supply sequence.

[0017] Secondly, embodiments of this application provide a coordinated resupply sequence generation device for a hybrid energy vehicle fleet, comprising: The acquisition module is used to acquire the supply demand information of each vehicle in the fleet. The supply demand information includes at least the required supply time. The required supply time is used to divide the vehicles in the fleet into long-term supply vehicles and short-term supply vehicles. The first allocation module is used to generate a first supply sequence for the long-term supply vehicle and allocate a corresponding first supply time window to the long-term supply vehicle. The second allocation module is used to dynamically insert a second supply sequence into the short-term supply vehicle within one or more time gaps formed by the first supply time window, and allocate a corresponding second supply time window. A generation module is used to generate a coordinated resupply sequence for the convoy based on the first resupply sequence and the second resupply sequence.

[0018] In one possible implementation, the first allocation module is configured to calculate a target supply station for the long-term supply vehicle based on the real-time status information of the supply station; calculate a target supply start time with the goal of minimizing the total waiting time of the long-term supply vehicle; and generate a first supply time window based on the target supply station, the target supply start time, and the supply time required by the vehicle.

[0019] In one possible implementation, the second allocation module is configured to identify the idle time gaps between all the first resupply time windows, and match the resupply tasks of the short-term resupply vehicles with the idle time gaps. The matching constraints include: the resupply time of the short-term resupply vehicle is less than or equal to the duration of the idle time gap, and the short-term resupply vehicle is spatially capable of reaching and utilizing the resupply station corresponding to the idle time gap; obtain the optimal matching scheme that satisfies the constraints, and generate the second resupply sequence.

[0020] In one possible implementation, the device further includes an execution module that performs the generation and adjustment of the coordinated supply sequence under a distributed architecture. Each vehicle or vehicle group in the fleet acts as a distributed node, and the nodes exchange their respective supply plans through vehicle-to-everything (V2X) communication. When any node detects a deviation from the supply plan, it triggers a local replanning and uses a distributed consensus algorithm to converge the local plans of each node to a new globally optimal or near-optimal target coordinated supply sequence.

[0021] In one possible implementation, the resupply requirement further includes one or more of the following: vehicle remaining energy, energy consumption rate, destination information, vehicle maximum energy capacity, and resupply rate.

[0022] In one possible implementation, the apparatus further includes a determination module for dynamically determining thresholds for the long-term supply vehicles and the short-term supply vehicles based on the median, average, or cluster analysis of the vehicle resupply times in the convoy.

[0023] Thirdly, embodiments of this application also provide an electronic device, which includes: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores instructions that can be executed by at least one processor to cause the electronic device to perform a method corresponding to any embodiment of the first aspect of the present application.

[0024] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement any of the methods described in the first aspect of embodiments of this application.

[0025] Fifthly, this disclosure also provides a computer program product comprising computer-executable instructions, which, when executed by a processor, are used to implement the methods of any embodiment corresponding to the first aspect of this disclosure.

[0026] In summary, the method provided in this application eliminates major latency bottlenecks by prioritizing deterministic time windows for long-term replenishment vehicles, thereby precisely embedding short-term replenishment tasks into idle time gaps to achieve parallel scheduling. Simultaneously, it innovatively introduces a distributed architecture, enabling nodes to quickly reach a globally optimal solution in a dynamic environment through a consensus algorithm. By integrating multi-dimensional replenishment demand data, the system constructs a refined energy management model. The technical solution achieves a fundamental shift from single-vehicle optimization to fleet collaboration, significantly improving resource utilization, transforming uncertain queuing into a deterministic parallel process, and ultimately effectively addressing the "weakest link" effect in mixed fleets, drastically reducing total fleet waiting time, and comprehensively improving operational efficiency and system robustness. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0028] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A schematic flowchart of a method for generating a coordinated resupply sequence for a hybrid energy vehicle fleet, provided in an embodiment of this application; Figure 2 This application provides a schematic flowchart of a method for classifying vehicles based on dynamic thresholds, as illustrated in an embodiment of the present application. Figure 3This application provides a schematic flowchart of a method for generating a first replenishment time window. Figure 4 This is a schematic flowchart of the second supply sequence generation method provided in the embodiments of this application; Figure 5 This is a schematic diagram of the replenishment time window generation method provided in the embodiments of this application; Figure 6 This application provides a schematic diagram of a collaborative resupply sequence generation device for a hybrid energy vehicle fleet; Figure 7 This is a schematic diagram of an electronic device for generating a coordinated resupply sequence for a hybrid energy vehicle fleet, provided as an embodiment of this application. Detailed Implementation

[0030] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0031] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0032] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0033] In this embodiment of the disclosure, the vehicles in the vehicle platoon may be, but are not limited to: multiple wheeled mobile robots, wheeled mobile robots, mobile robots, passenger cars, commercial vehicles (e.g., trucks, buses, vans, etc.), special purpose vehicles (e.g., ambulances, fire trucks, engineering vehicles, rescue vehicles, etc.), agricultural and industrial vehicles (e.g., harvesters, forklifts, etc.), transportation and logistics vehicles (e.g., container trucks, refrigerated trucks, etc.), new energy vehicles (e.g., electric vehicles, hybrid vehicles), and special vehicles (e.g., garbage trucks, water trucks, etc.).

[0034] In this embodiment, within a large-scale truck convoy, vehicles can communicate directly via V2V. Communication methods include, but are not limited to, Long Range Radio (LoRa) modules, Narrowband Internet of Things (NB-IoT) modules, Enhanced Machine-Type Communication (eMTC) modules, mobile communication, LTE-V (LTE-Vehicle-to-Everything), Dedicated Short-Range Communication (DSRC), cellular vehicle-to-everything (C-V2X), and vehicle-to-everything (V2X) wireless communication technologies. Understandably, in certain special scenarios, such as in remote areas without base station signals, installing communication modules on transport vehicles creates a local area network (LAN) between the convoy vehicles. This allows the lead vehicle and following vehicles to communicate via the LAN, ensuring safe vehicle operation.

[0035] Existing vehicle routing schemes primarily optimize individual vehicles, aiming to minimize travel time or energy consumption. Even when considering resupply factors, they only select the optimal resupply station for each vehicle, lacking a collaborative planning perspective that considers the overall operational efficiency of the fleet. This localized optimization of individual vehicles often leads to a loss of overall fleet operational efficiency.

[0036] Figure 1 This is a schematic flowchart illustrating a method for generating a coordinated resupply sequence for a hybrid energy vehicle fleet, provided in an embodiment of this application. Figure 1 The process includes steps S101, S102, S103, and S104. Each step is described in detail below.

[0037] Step S101: Obtain the resupply demand information of each vehicle in the convoy. The resupply demand information includes at least the required resupply time. The required resupply time is used to divide the vehicles in the convoy into long-term resupply vehicles and short-term resupply vehicles.

[0038] In one possible implementation, the method further includes: dynamically determining thresholds for long-term and short-term supply vehicles based on the median, average, or cluster analysis of the vehicle resupply times in the fleet. In this embodiment, the threshold can be a dynamic threshold. After obtaining fleet status and supply demand information, vehicles are classified based on the dynamic threshold. Figure 2 As shown, it mainly includes: S1011, Multi-source data acquisition. This means acquiring real-time static and dynamic vehicle data and real-time supply network data through onboard sensors, fleet management system (TMS), and vehicle-to-everything (V2X) communication.

[0039] The static and dynamic data of the vehicles include, but are not limited to, the real-time status of the vehicles, vehicle attributes, task information, and energy consumption models. The real-time status of the vehicles includes, but is not limited to, the precise geographical location of each vehicle and the current remaining energy (such as electric power, hydrogen, and fuel). Vehicle attributes include, but are not limited to, vehicle type (pure electric, hydrogen fuel, gasoline, etc.), maximum energy capacity, and energy replenishment rate. Task information includes, but is not limited to, the preset driving route, destination, and planned task duration. The energy consumption model includes, but is not limited to, the energy consumption rate calculated based on historical and real-time data.

[0040] The real-time data of the supply network is obtained in real time by accessing the back-end management system of each energy supply station (charging station, hydrogen refueling station, gas station), and mainly includes geographical location, energy type served, service capacity (such as the number of charging piles), real-time busyness, number of vehicles currently in queue, and estimated waiting time for each service pile.

[0041] S1012. Replenishment Requirement Calculation. This involves acquiring static and dynamic vehicle data, as well as real-time replenishment network data, to calculate the "replenishment time required" for each vehicle in the fleet. This includes determining whether a vehicle needs replenishment within the current mission cycle based on its remaining energy, energy consumption rate, and remaining mileage to its destination. For vehicles requiring replenishment, the estimated time required to complete the replenishment is precisely calculated based on their energy deficit (target energy minus remaining energy) and the replenishment rate corresponding to their vehicle type; this is the "replenishment time required."

[0042] S1013. Vehicle Classification Based on Dynamic Thresholds. This means the system does not use a fixed time threshold, but dynamically classifies vehicles requiring long-term or short-term resupply based on the specific composition of the current fleet, ensuring the rationality and adaptability of the classification. The system takes the set of "replenishment time required" for all vehicles in the fleet as input and calculates the classification threshold using one of the following three methods: Method 1: Calculate the median of all vehicle resupply times. For example, a convoy includes six vehicles. Arrange all resupply times of the six vehicles in ascending order [8, 10, 20, 25, 45, 50]. This sequence has a total of 6 data points (an even number). The median is the average of the 3rd and 4th values, which is (20 + 25) / 2 = 22.5 minutes.

[0043] Method 2: Calculate the average resupply time for all vehicles. For example, a convoy includes six vehicles. Arrange the total resupply times of the six vehicles in ascending order [8, 10, 20, 25, 45, 50]. Calculate the arithmetic mean of all resupply times: (8 + 10 + 20 + 25 + 45 + 50) / 6 = 158 / 6 ≈ 26.33 minutes. The dynamic threshold is determined to be 26.33 minutes.

[0044] Method 3: Employ a clustering algorithm (such as K-means) to automatically divide the refueling time of all vehicles into two clusters, using the boundary value between the clusters as the threshold. The system uses the K-means clustering algorithm (preset K=2) to divide the 6 refueling time data points into two clusters. After iterative calculation, the final clustering result is usually: Cluster 1 (short-time group): [8, 10, 20, 25], Cluster 2 (long-time group): [45, 50]. Find the boundary value between the two clusters. The maximum value of Cluster 1 is 25, and the minimum value of Cluster 2 is 45. The system can take the midpoint between these two values ​​as the threshold, i.e., (25 + 45) / 2 = 35 minutes. Alternatively, the maximum value of Cluster 1 (25 minutes) can be directly used as the upper bound of the threshold to ensure that long-time vehicles are effectively identified.

[0045] Vehicles whose "replenishment time required" is greater than the dynamic threshold are classified as long-term replenishment vehicles; vehicles whose "replenishment time required" is less than or equal to the dynamic threshold are classified as short-term replenishment vehicles.

[0046] For example, using a median threshold of 22.5 minutes, the vehicles with long-term resupply (resupply time > 22.5 minutes) are: Vehicle A (45 minutes), D (50 minutes), and F (25 minutes). The vehicles with short-term resupply (resupply time ≤ 22.5 minutes) are: Vehicle B (20 minutes), C (8 minutes), and E (10 minutes).

[0047] If an average threshold of 26.33 minutes is used, the following vehicle types are considered for long-term resupply (resupply time > 26.33 minutes): Vehicle A (45 minutes), Vehicle D (50 minutes). Vehicle types for short-term resupply (resupply time ≤ 26.33 minutes): Vehicle B (20 minutes), Vehicle C (8 minutes), Vehicle E (10 minutes), Vehicle F (25 minutes). If a clustering threshold of 35 minutes is used, the vehicles with long-term resupply (resupply time > 35 minutes) are: Vehicle A (45 minutes), D (50 minutes). The vehicles with short-term resupply (resupply time ≤ 35 minutes) are: Vehicle B (20 minutes), C (8 minutes), E (10 minutes), F (25 minutes).

[0048] In this embodiment, a dynamic threshold division mechanism is used to enable vehicle classification to adapt to the actual composition and task characteristics of a specific fleet, avoiding the mismatch problem that may be caused by a fixed threshold. This ensures that the collaborative scheduling strategy of "long vehicles in fixed windows and short vehicles in gaps" always maintains optimal matching with the real-time status of the fleet, thereby maximizing the generation efficiency and execution effect of the supply sequence.

[0049] In one possible implementation, the resupply requirement further includes one or more of the following: vehicle remaining energy, energy consumption rate, destination information, vehicle maximum energy capacity, and resupply rate.

[0050] In this embodiment, a refined vehicle energy profile is constructed by introducing multi-dimensional replenishment demand parameters. This means the system can quantitatively assess the urgency and feasibility of vehicle replenishment based on accurate energy situational awareness, thereby formulating a replenishment plan that meets both energy security boundaries and optimal operational efficiency, significantly improving the accuracy and reliability of replenishment sequence planning.

[0051] Step S102: Generate a first supply sequence for the long-term supply vehicle and allocate a corresponding first supply time window for the long-term supply vehicle.

[0052] In one possible implementation, allocating a corresponding first resupply time window for the long-term resupply vehicle includes: calculating a target resupply station for the long-term resupply vehicle based on the real-time status information of the resupply station; calculating a target resupply start time with the goal of minimizing the total waiting time of the long-term resupply vehicle; and generating the first resupply time window based on the target resupply station, the target resupply start time, and the resupply time required by the vehicle.

[0053] For example, Figure 3 This application provides a schematic flowchart of a method for generating a first replenishment time window, including steps S1021, S1022, and S1023. The steps are described in detail below.

[0054] Step S1021: Calculate the target supply station. This involves real-time data acquisition and preprocessing via the supply station management system's real-time data interface; acquiring the current number of available workstations, estimated queuing time, and equipment status indicators for each station; and standardizing the data to eliminate differences in data formats between different stations. A multi-objective decision function is established: Station Score = α × Path Directionality + β × Resource Availability + γ × Service Matching Degree.

[0055] Among them, path alignment (weight α=0.4) calculates the additional distance cost of a station deviating from the main path and assesses detour time loss (based on real-time traffic conditions). Resource availability (weight β=0.35) is calculated as follows: current idle resource ratio = idle workstations / total workstations; dynamic queuing prediction = current queued vehicles × average service time; and resource stability indicators (based on historical failure rate). Service matching degree (weight γ=0.25) is calculated as follows: maximum output power of the charging station ≥ vehicle charging demand; physical interface type matching verification; and hydrogen purity / fuel grade meeting requirements. Step S1022: Calculate the target resupply start time. The optimal start time is determined using dynamic programming. First, a model is established: Total waiting time cost = w1 × queuing wait + w2 × early arrival wait + w3 × urgency penalty.

[0056] Wherein: Queue waiting time = max(0, estimated queue time), Early arrival waiting time = max(0, planned start time - earliest available start time), Urgency penalty: based on the urgency coefficient of the vehicle's remaining range. Using a 15-minute time granularity, a search is performed on each candidate start time t_i within the interval [earliest start time, latest start time]. The resource reservation status for time slot t_i is queried from the target site, and the estimated queue time for that time slot is calculated. After calculation, the total waiting time cost is evaluated, and the time point with the lowest total cost is finally selected as the target start time. Simultaneously, a resource reservation request is sent to the target site. If the request is rejected, it reverts to the second-best time point and retryes, with a maximum of 3 retries to ensure a high reservation success rate.

[0057] Step S1023: Generate the first resupply time window. When determining the time window parameters, the system generates structured time window data with clearly defined start and end times based on the selected target resupply station, the optimized resupply start time, and the estimated resupply duration including a safety buffer. This process comprehensively considers the station resource reservation confirmation status, vehicle arrival feasibility verification, and conflict detection results with existing plans. The final output is a complete time window scheme containing primary and backup station information, precise time intervals, and reliability assessments, ensuring that each parameter undergoes multi-dimensional verification to guarantee the reliability of execution.

[0058] After the time window is generated, the system immediately executes a conflict detection and resolution process: First, it checks whether there are overlapping time windows at the same station and verifies whether vehicles can arrive on time based on real-time route planning; if a conflict is detected, a local replanning mechanism is initiated, prioritizing adjustments to the plans of non-long-duration vehicles, and then fine-tuning the start time of the current vehicles within ±30 minutes. Simultaneously, the system performs a time window reliability assessment, calculating the execution success rate by analyzing historical data and generating a credibility index by comprehensively considering risk factors such as traffic delays and equipment failures. When this index falls below a preset threshold, a backup plan is automatically activated to ensure the robustness of the supply plan.

[0059] In this embodiment of the application, by intelligently matching target supply stations and planning the optimal supply time window for long-term supply vehicles, the uncertain queuing and waiting is transformed into deterministic planning, eliminating the main delay in the fleet supply process from the source and providing an opportunity for the parallel insertion of subsequent short-term vehicles.

[0060] Step S103: Within one or more time gaps formed by the first replenishment time window, dynamically insert a second replenishment sequence for the short-term replenishment vehicle and allocate a corresponding second replenishment time window.

[0061] For example, Figure 4 This is a schematic flowchart of the second supply sequence generation method provided in the embodiments of this application. It includes steps S1031, S1032, S1033, and S1034. Each step is described in detail below.

[0062] Step S1031: Idle Time Gap Identification and Feature Extraction. First, the first resupply time window sequence of all long-duration resupply vehicles is analyzed. Idle gaps are identified by calculating the time difference between adjacent time windows, and the available duration of each gap is precisely quantified. Based on this, a feature annotation algorithm is used to classify gaps into three categories: rigid gaps (fixed duration), elastic gaps (expandable), and boundary gaps (both ends of the task sequence). Simultaneously, the geographical location and resource type corresponding to each gap are recorded, providing structured input data for subsequent matching.

[0063] Step S1032: Spatiotemporal Feasibility Matching Analysis. Based on the identified gaps, the system performs dual constraint verification. The temporal constraint verification requires that the short-term vehicle resupply time plus a safety buffer must be less than or equal to the gap duration; the spatial constraint verification calculates the travel time using real-time road conditions to ensure that vehicles can arrive at the corresponding resupply station before the gap begins, and verifies the station resource compatibility. This step uses multi-dimensional condition filtering to quickly select all theoretically feasible matching combinations.

[0064] Step S1033: Solving for the optimal matching scheme. A weighted greedy algorithm combined with a backtracking strategy is used for optimal matching. First, a comprehensive score is calculated for each feasible match, taking into account indicators such as time utilization, path directionality, and resource sufficiency. Then, gap resources are allocated according to score priority, and conflict detection is used to avoid duplicate occupation. If local conflicts or resource competition occur, the backtracking mechanism is activated to reallocate resources, or the time arrangement is adjusted within the elastic gap to pursue the globally optimal solution.

[0065] Step S1034: Generation and Verification of the Second Supply Sequence. The system generates a structured second supply sequence from the optimization results, clearly defining the supply station, time window, and preceding and following task relationships for each short-term vehicle. Before output, a triple verification is performed: time continuity check to ensure reasonable task connection, resource conflict detection to prevent over-booking, and route feasibility verification based on real-time traffic prediction arrival time. Simultaneously, a backup plan is provided for each sequence, and monitoring thresholds are set to trigger dynamic adjustments, ensuring the robustness and reliability of the plan.

[0066] In this embodiment, by precisely embedding short-term resupply tasks into the idle time window formed by long-term resupply, a fundamental shift from serial waiting to parallel collaboration in the fleet resupply process is achieved. This fully leverages the time fragment resources in task scheduling, enabling short-term vehicles to complete resupply without affecting the critical path, thereby minimizing the fleet's ineffective waiting time and significantly improving overall operational efficiency and resource utilization.

[0067] In one possible implementation, dynamically inserting the second supply sequence for the short-term supply vehicle includes: identifying the idle time gaps between all the first supply time windows, and matching the supply task of the short-term supply vehicle with the idle time gaps. The matching constraints include: the supply time of the short-term supply vehicle is less than or equal to the duration of the idle time gap, and the short-term supply vehicle is spatially capable of reaching and utilizing the supply station corresponding to the idle time gap; obtaining the optimal matching scheme that satisfies the constraints, and generating the second supply sequence.

[0068] For example, Figure 5 This is a schematic flowchart of the replenishment time window generation method provided in the embodiments of this application. It includes steps S103a, S103b, and S103c. Each step is described in detail below.

[0069] Step S103a: Time gap resource processing. The system first establishes a fleet replenishment timeline based on the first replenishment time window. It then automatically extracts idle periods between adjacent long-duration tasks using a gap identification algorithm and classifies them into three categories based on duration: Category A (>30 minutes), Category B (15-30 minutes), and Category C (5-15 minutes). Subsequently, a multi-factor evaluation model is used to quantify the value of each gap, comprehensively considering duration coefficients, geographical location weights, and resource sufficiency to form a structured schedulable time resource pool.

[0070] Step S103b: Dynamic Matching and Conflict Resolution. Based on resource-based time gaps, the system establishes a multi-constraint matching model to rigorously verify time feasibility (replenishment time + buffer ≤ gap duration), spatial feasibility (whether on-time arrival is possible), and resource compatibility. An intelligent matching algorithm with priority ranking allocates optimal gaps to short-term vehicles and performs real-time conflict detection. When resource contention or path conflicts occur, resolution strategies such as time fine-tuning, station switching, or task splitting are automatically triggered to ensure the global feasibility of the matching scheme.

[0071] Step S103c: Supply Time Window Generation. The system will generate supply time windows accurate to the second based on the optimized matching results, clearly defining the supply station, start and end times, and associated preceding and following task contexts for each short-term supply vehicle. Each time window is equipped with a primary and backup station plan and execution buffer guarantee, and an embedded real-time monitoring mechanism will be used to dynamically activate the backup plan once an execution deviation is predicted. Finally, a structured second supply sequence will be output to ensure the efficient and reliable insertion of short-term supply tasks.

[0072] Step S104: Generate a coordinated supply sequence for the convoy based on the first supply sequence and the second supply sequence.

[0073] In this embodiment, after the independent generation of the first and second supply sequences is completed, the system integrates the two types of sequences through a time-series fusion engine. Based on a unified time axis, the fixed time windows of long-term supply vehicles and the dynamic insertion windows of short-term supply vehicles are sorted and connected, resource conflicts and time overlaps are automatically eliminated, and a global buffer strategy is injected. Finally, a global supply Gantt chart of the fleet with complete structure, reasonable timing, and coordinated resources is generated. This coordinated supply sequence clearly defines the corresponding execution relationship between each vehicle and the designated supply station within a specific time window, forming a final scheduling scheme that can be directly issued and executed.

[0074] In one possible implementation, the generation and adjustment of the coordinated supply sequence are performed under a distributed architecture, including: each vehicle or vehicle group in the fleet acts as a distributed node, and the nodes exchange their respective supply plans through vehicle-to-everything (V2X) communication; when any node detects a deviation from the supply plan, it triggers a local replanning, and a distributed consensus algorithm is used to converge the local plans of each node to a new globally optimal or near-optimal target coordinated supply sequence.

[0075] In this embodiment, a distributed architecture decomposes the centralized planning task into parallel processing across vehicle nodes. When a single node deviates from its plan, the system can quickly reach a new globally optimal solution through local replanning and distributed negotiation, achieving a leap from static planning to dynamic adaptation in fleet resupply scheduling. The decentralized collaboration mechanism significantly improves the system's response speed and robustness to emergencies, ensuring that the hybrid energy fleet maintains efficient collaborative resupply capabilities in dynamically changing environments.

[0076] In summary, the method provided in this application eliminates major latency bottlenecks by prioritizing deterministic time windows for long-term replenishment vehicles, thereby precisely embedding short-term replenishment tasks into idle time gaps to achieve parallel scheduling. Simultaneously, it innovatively introduces a distributed architecture, enabling nodes to quickly reach a globally optimal solution in a dynamic environment through a consensus algorithm. By integrating multi-dimensional replenishment demand data, the system constructs a refined energy management model. The technical solution achieves a fundamental shift from single-vehicle optimization to fleet collaboration, significantly improving resource utilization, transforming uncertain queuing into a deterministic parallel process, and ultimately effectively addressing the "weakest link" effect in mixed fleets, drastically reducing total fleet waiting time, and comprehensively improving operational efficiency and system robustness.

[0077] Figure 6 This application provides a schematic diagram of a coordinated resupply sequence generation device for a hybrid energy vehicle fleet, including: The acquisition module 601 is used to acquire the supply demand information of each vehicle in the fleet. The supply demand information includes at least the required supply time. The required supply time is used to divide the vehicles in the fleet into long-term supply vehicles and short-term supply vehicles. The first allocation module 602 is used to generate a first supply sequence for the long-term supply vehicle and allocate a corresponding first supply time window to the long-term supply vehicle. The second allocation module 603 is used to dynamically insert a second supply sequence into the short-term supply vehicle within one or more time gaps formed by the first supply time window, and allocate a corresponding second supply time window. The generation module 604 is used to generate a coordinated supply sequence for the convoy based on the first supply sequence and the second supply sequence.

[0078] In one possible implementation, the first allocation module is configured to calculate a target supply station for the long-term supply vehicle based on the real-time status information of the supply station; calculate a target supply start time with the goal of minimizing the total waiting time of the long-term supply vehicle; and generate a first supply time window based on the target supply station, the target supply start time, and the supply time required by the vehicle.

[0079] In one possible implementation, the second allocation module is configured to identify the idle time gaps between all the first resupply time windows, and match the resupply tasks of the short-term resupply vehicles with the idle time gaps. The matching constraints include: the resupply time of the short-term resupply vehicle is less than or equal to the duration of the idle time gap, and the short-term resupply vehicle is spatially capable of reaching and utilizing the resupply station corresponding to the idle time gap; obtain the optimal matching scheme that satisfies the constraints, and generate the second resupply sequence.

[0080] In one possible implementation, the device further includes an execution module that performs the generation and adjustment of the coordinated supply sequence under a distributed architecture. Each vehicle or vehicle group in the fleet acts as a distributed node, and the nodes exchange their respective supply plans through vehicle-to-everything (V2X) communication. When any node detects a deviation from the supply plan, it triggers a local replanning and uses a distributed consensus algorithm to converge the local plans of each node to a new globally optimal or near-optimal target coordinated supply sequence.

[0081] In one possible implementation, the resupply requirement further includes one or more of the following: vehicle remaining energy, energy consumption rate, destination information, vehicle maximum energy capacity, and resupply rate.

[0082] In one possible implementation, the apparatus further includes a determination module for dynamically determining thresholds for the long-term supply vehicles and the short-term supply vehicles based on the median, average, or cluster analysis of the vehicle resupply times in the convoy.

[0083] In one possible implementation, the device is used to achieve Figures 1 to 5 Any of the method embodiments.

[0084] Figure 7 This is a schematic diagram of an electronic device for generating a coordinated resupply sequence for a hybrid energy vehicle fleet, provided as an embodiment of this application. Figure 7 As shown, the electronic device 700 includes a memory 710 and a processor 720.

[0085] The memory 710 stores a computer program that can be executed by at least one processor 720. This computer program is executed by at least one processor 720 to cause the electronic device to implement the methods provided in any of the above embodiments.

[0086] The memory 710 and the processor 720 can be connected via a bus 730.

[0087] The relevant explanations can be understood by referring to the corresponding descriptions and effects in the method embodiments, and will not be repeated here.

[0088] One embodiment of this application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to perform the following: Figures 1 to 5 The method provided in any of the corresponding embodiments.

[0089] The computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0090] One embodiment of this application provides a computer program product comprising computer-executable instructions, which, when executed by a processor, are used to implement, as described in 1 to... Figure 5 The method provided in any corresponding embodiment.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0092] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope of this application is indicated by the claims.

Claims

1. A method for generating a coordinated resupply sequence for a hybrid energy vehicle fleet, characterized in that, include: Obtain the resupply requirement information of each vehicle in the convoy. The resupply requirement information includes at least the required resupply time. The required resupply time is used to divide the vehicles in the convoy into long-term resupply vehicles and short-term resupply vehicles. A first supply sequence is generated for the long-term supply vehicle, and a corresponding first supply time window is allocated to the long-term supply vehicle; Within one or more time gaps formed by the first replenishment time window, a second replenishment sequence is dynamically inserted for the short-term replenishment vehicle, and a corresponding second replenishment time window is allocated; A coordinated resupply sequence for the convoy is generated based on the first resupply sequence and the second resupply sequence.

2. The method according to claim 1, characterized in that, The allocation of a corresponding first resupply time window to the long-duration resupply vehicle includes: Based on the real-time status information of the supply station, the target supply station is calculated for the long-term supply vehicle; The target resupply start time is calculated with the objective of minimizing the total waiting time of the long-duration resupply vehicles. The first resupply time window is generated based on the target resupply station, the target resupply start time, and the resupply time required by the vehicle.

3. The method according to claim 1, characterized in that, The dynamic insertion of a second supply sequence into the short-term supply vehicle includes: Identify the idle time gaps between all the first resupply time windows, and match the resupply tasks of the short-term resupply vehicles with the idle time gaps. The matching constraints include: The resupply time of the short-term resupply vehicle is less than or equal to the duration of the idle time gap, and the short-term resupply vehicle is spatially able to reach and utilize the resupply station corresponding to the idle time gap; Obtain the optimal matching scheme that satisfies the constraints, and generate the second supply sequence.

4. The method according to any one of claims 1-3, characterized in that, The generation and adjustment of the coordinated supply sequence are performed under a distributed architecture, including: Each vehicle or vehicle group in the convoy acts as a distributed node, and the nodes exchange their respective resupply plans through vehicle network communication. When any node detects a deviation from the supply plan, it triggers a local replanning and uses a distributed consensus algorithm to converge the local plans of each node to a new globally optimal or near-optimal target collaborative supply sequence.

5. The method according to any one of claims 1-4, characterized in that, The resupply requirements also include one or more of the following: vehicle remaining energy, energy consumption rate, destination information, vehicle maximum energy capacity, and resupply rate.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: The thresholds for the long-term supply vehicles and the short-term supply vehicles are determined dynamically based on the median, average, or cluster analysis of the supply times of the vehicles in the convoy.

7. A device for generating a coordinated resupply sequence for a hybrid energy vehicle fleet, characterized in that, include: The acquisition module is used to acquire the supply demand information of each vehicle in the fleet. The supply demand information includes at least the required supply time. The required supply time is used to divide the vehicles in the fleet into long-term supply vehicles and short-term supply vehicles. The first allocation module is used to generate a first supply sequence for the long-term supply vehicle and allocate a corresponding first supply time window to the long-term supply vehicle. The second allocation module is used to dynamically insert a second supply sequence into the short-term supply vehicle within one or more time gaps formed by the first supply time window, and allocate a corresponding second supply time window. A generation module is used to generate a coordinated resupply sequence for the convoy based on the first resupply sequence and the second resupply sequence.

8. A computer-readable storage medium, characterized in that, It stores a computer program thereon, which is executed by a processor to implement the method of any one of claims 1 to 6.

9. A computer program product comprising a computer-readable storage medium on which a computer program is stored, the computer program, when executed by a processor, implementing the method as described in any one of claims 1 to 6.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 6.

Images