Energy efficiency optimization task management method and related devices under vehicle-road-cloud communication architecture

Abstract

This application discloses an energy efficiency optimization task management method and related apparatus under a vehicle-road-cloud communication architecture, relating to the field of hybrid electric vehicle (HEV) energy efficiency optimization technology. The method includes: acquiring the status of HEVs on a target road segment; obtaining control commands corresponding to the HEVs through a hybrid electric vehicle (HEV) system energy efficiency optimization task management strategy model; and sending the control commands to the HEVs. The status includes engine speed, vehicle speed, and battery state of charge. The control commands include the output power allocation ratio between the battery and the engine. The HEV system energy efficiency optimization task management strategy model is trained based on representative driving conditions generated from historical speed data of several vehicles on the target road segment. This application enables energy efficiency optimization task management for all HEVs traveling on the same road segment, improving the efficiency and accuracy of HEV system energy optimization task management and expanding its applicability.

Description

Technical Field

[0001] This application relates to the field of energy efficiency optimization technology for hybrid electric vehicles, and in particular to a method and related apparatus for energy efficiency optimization task management under a vehicle-road-cloud communication architecture. Background Technology

[0002] With the rapid development of automotive powertrain systems, electrification is playing an increasingly important role in vehicle power, and hybrid power has become one of the most effective technologies for reducing fuel consumption. Hybrid technology increases the vehicle's power source and enhances the flexibility of energy management. Energy efficiency optimization task management technology based on road condition prediction is gradually gaining attention.

[0003] Currently, most hybrid power system energy efficiency optimization task management based on road condition prediction focuses on a single vehicle perspective. For example, for a single vehicle, historical speed data is collected, and a network model is trained to predict future speeds based on the vehicle's speed within a past time window. This predicted speed is then used to manage energy efficiency optimization tasks within the future time window. This single-vehicle-based approach is generally suitable for situations where the vehicle frequently travels on the same road segment. However, it cannot effectively manage hybrid power system energy efficiency optimization tasks on road segments that the vehicle does not frequently travel on. Summary of the Invention

[0004] The purpose of this application is to provide a method and related device for energy efficiency optimization task management under a vehicle-road-cloud communication architecture, which can effectively improve the efficiency and accuracy of energy efficiency optimization task management for hybrid vehicles and expand the scope of energy efficiency optimization task management for hybrid systems.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] Firstly, this application provides a method for managing energy efficiency optimization tasks under a vehicle-road-cloud communication architecture, including:

[0007] The status of hybrid vehicles on the target road segment is obtained; the status includes engine speed, vehicle speed, and power battery state of charge.

[0008] Based on the state of the hybrid vehicle and the hybrid system energy efficiency optimization task management strategy model, control commands corresponding to the hybrid vehicle are obtained; the control commands include the output power distribution ratio of the power battery and the engine; the hybrid system energy efficiency optimization task management strategy model is trained based on representative driving conditions of the target road segment; the representative driving conditions are generated based on the historical speed data of several vehicles on the target road segment.

[0009] Control commands are sent to the hybrid vehicle.

[0010] Secondly, this application provides an energy efficiency optimization task management system under a vehicle-road-cloud communication architecture, the system comprising: roadside equipment (RSE) and a cloud platform; wherein,

[0011] The roadside equipment (RSE) is used to acquire historical speed data of several vehicles on the target road segment and the status of hybrid vehicles; based on the historical speed data of several vehicles on the target road segment, it generates representative driving conditions for the target road segment; and sends the representative driving conditions and the status of hybrid vehicles on the target road segment to the cloud platform.

[0012] The cloud platform is used to execute the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture described in the first aspect.

[0013] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture described in the first aspect.

[0014] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture described in the first aspect.

[0015] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture described in the first aspect.

[0016] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0017] This application provides a method and related apparatus for energy efficiency optimization task management under a vehicle-road-cloud communication architecture. The method includes: acquiring the status of hybrid vehicles on a target road segment; obtaining control commands corresponding to the hybrid vehicles based on their status and a hybrid system energy efficiency optimization task management strategy model; and sending the control commands to the hybrid vehicles. The status includes engine speed, vehicle speed, and battery state of charge. The control commands include the output power distribution ratio between the battery and the engine. The hybrid system energy efficiency optimization task management strategy model is trained based on representative driving conditions generated from historical speed data of several vehicles on the target road segment. Compared to existing methods for managing hybrid system energy efficiency optimization tasks for a single vehicle, the above solution of this application can achieve energy efficiency optimization task management for all hybrid vehicles traveling on the same road segment, improving the efficiency and accuracy of hybrid system energy optimization task management. Even if a hybrid vehicle has not traveled on that road segment, energy efficiency optimization task management can still be performed on it, expanding the scope of hybrid system energy efficiency optimization task management. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating an energy efficiency optimization task management method under a vehicle-road-cloud communication architecture, provided as an embodiment of this application;

[0020] Figure 2 A schematic diagram of functional modules of an energy efficiency optimization task management system under a vehicle-road-cloud communication architecture provided in an embodiment of this application;

[0021] Figure 3 A schematic diagram of a hybrid electric vehicle energy efficiency optimization management system framework based on a vehicle-road-cloud cooperative communication architecture is provided in one embodiment of this application.

[0022] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] The automotive industry is witnessing a transformative era driven by the convergence of intelligent connected vehicles and advanced communication technologies. Intelligent connected vehicles, powered by vehicle-to-everything (V2X) communication, have become a promising paradigm for improving vehicle performance, safety, and efficiency. Particularly in the hybrid electric vehicle (HEV) sector, the synergy between vehicle-to-infrastructure (V2I) and cloud-based communication architectures offers unprecedented opportunities for energy efficiency optimization management (also known as energy efficiency optimization task management). Through information sharing within this architecture, HEVs can dynamically adjust their operating parameters based on environmental conditions, traffic patterns, and road topology, thereby maximizing energy efficiency and minimizing fuel consumption. However, current technologies do not fully utilize the road condition reconstruction capabilities of V2I architectures, thus somewhat reducing the performance of energy efficiency optimization management tasks.

[0025] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] See Figure 1 In one exemplary embodiment, an energy efficiency optimization task management method under a vehicle-road-cloud communication architecture is provided, the method comprising the following steps:

[0027] Step 101: Obtain the status of the hybrid vehicles on the target road segment; the status includes engine speed, vehicle speed, and power battery state of charge.

[0028] Step 102: Based on the state of the hybrid vehicle and the hybrid system energy efficiency optimization task management strategy model (hereinafter referred to as the strategy model or energy efficiency optimization task management strategy), obtain the control command corresponding to the hybrid vehicle; the control command includes the output power distribution ratio of the power battery and the engine; the hybrid system energy efficiency optimization task management strategy model is trained based on the representative driving conditions of the target road segment; the representative driving conditions (hereinafter referred to as representative conditions) are generated based on the historical speed data of several vehicles on the target road segment.

[0029] Step 103: Send control commands to the hybrid vehicle.

[0030] As an optional implementation, the training process of the hybrid power system energy efficiency optimization task management strategy model specifically includes the following steps:

[0031] Step 201: Based on the hybrid power model, determine the reinforcement learning algorithm model and reward function; the hybrid power model is used to output the state at the next moment based on the current state, control commands, and the representative driving condition; the reward function is used to calculate the environmental reward. During training, the change in vehicle speed in the state output by the hybrid power model conforms to the vehicle speed curve corresponding to the representative driving condition.

[0032] Step 202: Determine the environment corresponding to the reinforcement learning algorithm model based on the representative driving conditions, the hybrid power model, and the reward function.

[0033] Step 203: Train the reinforcement learning algorithm model according to the environment to obtain a trained reinforcement learning algorithm model.

[0034] Step 204: Determine the energy efficiency optimization task management strategy model for the hybrid power system based on the trained reinforcement learning algorithm model.

[0035] In some embodiments, the training process can be periodic, such as reconstructing road conditions (i.e. generating representative driving conditions) every week. If the road conditions reconstructed this week are only slightly different from those of last week (which can be determined by comparing the distribution of vehicle speed and acceleration), then the policy model does not need to be trained or optimized. If the reconstructed road conditions change significantly, then the policy model needs to be trained and optimized again.

[0036] As an optional implementation, the SAC (soft actor-critic) algorithm can be used during the training process of the hybrid power system energy efficiency optimization task management strategy model to obtain the optimal strategy model according to the following process:

[0037] A2C reinforcement learning algorithm update process:

[0038] Input: s t ,a t ,r t ,s t+1 ,a t+1 ;

[0039] 1:δ t =V(s) t ;w)-r t -γV(s t+1 ;w);

[0040] 2:

[0041] 3:

[0042] 4:s t ←s t+1 ,a t ←a t+1 ;

[0043] Finish.

[0044] Where δ represents the temporal difference value of the actor policy network, V represents the actor policy network (a nonlinear mapping from state s to action a), w represents the network parameters corresponding to the actor policy network, γ represents the discount factor (usually a constant less than 1), π represents the critic evaluation network, θ represents the parameters of the critic evaluation network, and β represents the update step size. This represents gradient operation.

[0045] The actor policy network obtained by training and solving through the above reinforcement learning algorithm is the trained hybrid power system energy efficiency optimization task management policy model.

[0046] As an optional implementation, the state equation expression for the power system corresponding to the hybrid power model is as follows:

[0047] s t+1 =f(s) t ,u t );

[0048] Among them, s t+1 This indicates the state of the powertrain at time t+1, including engine speed, vehicle speed, and the state-of-charge (SoC) of the battery; s t u represents the state of the dynamic system at time t; t This represents the control command (control parameter) at time t, i.e., the power distribution ratio between the power battery and the engine.

[0049] The above state equations are established based on the powertrain topology connection method of hybrid vehicles.

[0050] As an optional implementation, the reward function expression is as follows:

[0051]

[0052] Where r represents environmental reward; Indicates the engine's instantaneous fuel consumption, also known as fuel consumption rate; SoC refThe reference state of charge (SOC) is represented (usually a fixed value, such as 60%); SoC(t) represents the state of charge of the power battery at time t; α and β represent the weighting coefficients of the corresponding terms.

[0053] The reward function shows that the control objective of the hybrid power system energy efficiency optimization task management strategy is mainly to minimize engine fuel consumption, while also taking into account the power battery SoC at the reference SoC value (i.e., SoC). ref Fluctuations around )

[0054] As an optional implementation, the process of generating the representative driving condition (i.e., the road condition reconstruction process) specifically includes the following steps:

[0055] Step 301: Calculate the historical acceleration data of several vehicles based on their historical speed data for the target road segment.

[0056] Step 302: Divide the historical speed data and historical acceleration data of several vehicles on the target road segment into several discrete intervals.

[0057] Step 303: Determine the state probability transition matrix corresponding to each discrete interval.

[0058] Step 304: Based on the state probability transition matrix corresponding to each discrete interval, generate representative driving conditions for the target road segment.

[0059] As an optional implementation, step 304 specifically includes:

[0060] Step 304.1: Set the initial state corresponding to the driving condition; the initial state includes the speed and acceleration at the start time of the target road segment.

[0061] Step 304.2: Randomly sample the state probability transition matrix to obtain the velocity and acceleration at the next moment.

[0062] Step 304.3: Determine whether the driving condition has reached the termination state; the termination state includes the speed at the end time of the target road segment and the total mileage corresponding to the driving condition; the total mileage corresponding to the driving condition is the mileage of the target road segment.

[0063] Step 304.4: If not, return to step 304.2 until the termination state is reached, and the first driving condition is obtained.

[0064] Step 304.5: Determine whether the first driving condition meets the characteristic value deviation requirement; if it does, then determine the first driving condition as the representative driving condition of the target road segment.

[0065] See Figure 2 and Figure 3 Based on the same inventive concept, embodiments of this application also provide an energy efficiency optimization task management system under a vehicle-road-cloud communication architecture, the system including roadside equipment (RSE) and a cloud platform; wherein,

[0066] The roadside equipment (RSE) is used to acquire historical speed data of several vehicles on the target road segment and the status of hybrid vehicles; based on the historical speed data of several vehicles on the target road segment, it generates representative driving conditions for the target road segment; and sends the representative driving conditions and the status of hybrid vehicles on the target road segment to the cloud platform. Figure 3 The roadside in the text refers to the roadside equipment (RSE).

[0067] The cloud platform is used to execute the steps in the above-described method embodiments, namely: training the hybrid power system energy efficiency optimization task management strategy model based on representative driving conditions of the target road segment to obtain a trained hybrid power system energy efficiency optimization task management strategy model; obtaining the control command corresponding to the hybrid power vehicle based on the trained hybrid power system energy efficiency optimization task management strategy model and the state of the hybrid power vehicle; and sending the control command to the hybrid power vehicle.

[0068] The hybrid vehicle energy efficiency optimization task management strategy provided in this embodiment, which is oriented towards vehicle-road-cloud communication architecture, explores the potential of vehicle-road-cloud communication information to improve the economy of hybrid vehicles by reconstructing road conditions based on historical data.

[0069] Figure 3 This paper describes the overall framework for managing energy efficiency optimization tasks in hybrid vehicles using domain control within a vehicle-road-cloud cooperative communication architecture. First, vehicles on the road send their driving speeds, collected by the intelligent driving domain controller, to the roadside equipment (RSE). Then, the RSE generates representative driving conditions (i.e., characteristic speeds over a period of time) based on the received vehicle speeds. This generation of representative conditions is often referred to as road condition reconstruction or driving condition reconstruction, and it is sent to the cloud platform. Finally, the cloud platform trains an energy efficiency optimization task management strategy based on reinforcement learning algorithms using the generated representative driving conditions, and sends the control commands output by the strategy to the vehicle's powertrain domain controller for execution. The generated representative driving conditions reflect the vehicle's driving status, thus making the trained energy efficiency optimization task management strategy more suitable for vehicles on roads near the RSE. This architecture employs two domain controllers: an intelligent driving domain controller and a powertrain domain controller, used for historical speed data collection and storage, and for executing hybrid power allocation, respectively. This approach of assigning different tasks to different domain controllers facilitates a balance of computational burden.

[0070] The energy efficiency optimization task management method under the vehicle-road-cloud communication architecture provided in this application can also be described as the following process:

[0071] Step 401: Reconstruct driving conditions and generate representative driving conditions.

[0072] In this application, road condition reconstruction is mainly based on the reconstruction of characteristic driving conditions using a state probability transition matrix. First, vehicle speed and acceleration are divided into several discretized intervals with a certain degree of dispersion. Within each corresponding speed and acceleration discrete interval, the corresponding state probability transition matrix is ​​calculated. Then, an initial state for vehicle speed and acceleration is set, and the state at the next moment is obtained by randomly sampling the state probability transition matrix, until a predetermined termination state is reached. Next, the characteristic values ​​of the generated driving condition (i.e., the first driving condition) are calculated. These characteristic values ​​include the root mean square error of speed, average positive acceleration, average negative acceleration, the root mean square error of positive acceleration, and the number of stops per kilometer. If the above characteristic values ​​meet the deviation requirements, the generated characteristic driving condition is considered valid. Otherwise, the above process based on the state probability transition matrix can be repeated to generate new driving conditions until the generated new driving conditions meet the characteristic value deviation requirements, thereby obtaining the characteristic driving condition (i.e., the representative driving condition).

[0073] In some embodiments, the initial state of both vehicle speed and acceleration is set to 0.

[0074] In some embodiments, the specified termination state is: the vehicle speed is 0, and the total mileage of the generated condition reaches the average mileage of the condition dataset collected by the roadside unit RSE.

[0075] In some embodiments, the criterion for determining whether the generated working condition meets the feature value deviation requirement is that the feature value of the generated working condition deviates from the feature value of the working condition dataset by less than 5%. The feature value of the working condition dataset is the average of the feature values ​​corresponding to each working condition in the dataset. Each working condition in the dataset represents the vehicle speed uploaded by different vehicles and the corresponding acceleration (this acceleration can be calculated based on the uploaded vehicle speed).

[0076] In some other embodiments, the initial and final states of vehicle speed are set to the average speed of the target road segment.

[0077] Step 402 involves modeling the energy efficiency optimization management task, specifically determining the state equation and reward function for the task. Then, a hybrid power model is constructed based on the state equation; and the training environment is determined based on representative driving conditions, the hybrid power model, and the reward function.

[0078] Step 403: Solving the energy efficiency optimization management task based on reinforcement learning. After determining the state equation and reward function of the energy efficiency optimization management task, the policy can be solved using any algorithm (such as the A2C reinforcement learning algorithm) within the reinforcement learning framework.

[0079] This application also provides an application scenario in which the energy efficiency optimization task management method under the above-described vehicle-road-cloud communication architecture is applied. Specifically, the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture provided in this embodiment can be applied to scenarios involving energy efficiency optimization task management for moving hybrid vehicles.

[0080] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, the computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements an energy efficiency optimization task management method under a vehicle-road-cloud communication architecture.

[0081] Those skilled in the art will understand that Figure 4 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0082] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0083] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0084] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0085] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0086] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0087] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for energy efficiency optimization task management under a vehicle-road-cloud communication architecture, characterized in that, The energy efficiency optimization task management method under the vehicle-road-cloud communication architecture includes: Acquire the status of hybrid vehicles on the target road segment; the status includes engine speed, vehicle speed, and battery state of charge. Based on the state of the hybrid vehicle and the hybrid system energy efficiency optimization task management strategy model, control commands corresponding to the hybrid vehicle are obtained; the control commands include the output power distribution ratio of the power battery and the engine; the hybrid system energy efficiency optimization task management strategy model is trained based on representative driving conditions of the target road segment; the representative driving conditions are generated based on historical speed data of several vehicles on the target road segment. Send control commands to the hybrid vehicle; The process of generating the representative driving conditions specifically includes: Based on the historical speed data of several vehicles on the target road segment, the historical acceleration data of several vehicles are calculated; the historical speed data and the historical acceleration data of several vehicles on the target road segment are divided into several discrete intervals; the state probability transition matrix corresponding to each discrete interval is determined; based on the state probability transition matrix corresponding to each discrete interval, a representative driving condition of the target road segment is generated. The step of generating representative driving conditions for the target road segment based on the state probability transition matrix corresponding to each discrete interval specifically includes: Set the initial state corresponding to the driving condition; the initial state includes the speed and acceleration at the start time of the target road segment; randomly sample the state probability transition matrix to obtain the speed and acceleration at the next moment; determine whether the termination state corresponding to the driving condition has been reached; the termination state includes the speed at the end time of the target road segment and the total mileage corresponding to the driving condition; the total mileage corresponding to the driving condition is the mileage of the target road segment; if not, return to the step "randomly sample the state probability transition matrix to obtain the vehicle speed and vehicle acceleration at the next moment" until the termination state is reached to obtain the first driving condition; determine whether the first driving condition meets the feature value deviation requirement; if it does, determine the first driving condition as the representative driving condition of the target road segment.

2. The energy efficiency optimization task management method under the vehicle-road-cloud communication architecture according to claim 1, characterized in that, The training process of the hybrid power system energy efficiency optimization task management strategy model specifically includes: Based on the hybrid power model, a reinforcement learning algorithm model and a reward function are determined; the hybrid power model is used to output the state at the next moment based on the current state, control commands, and the representative driving conditions; the reward function is used to calculate environmental rewards. Based on the representative driving conditions, the hybrid power model, and the reward function, the environment corresponding to the reinforcement learning algorithm model is determined. The reinforcement learning algorithm model is trained according to the environment to obtain a trained reinforcement learning algorithm model; Based on the trained reinforcement learning algorithm model, a task management strategy model for energy efficiency optimization of hybrid power systems is determined.

3. The energy efficiency optimization task management method under the vehicle-road-cloud communication architecture according to claim 2, characterized in that, The state equation expression for the power system corresponding to the hybrid power model is as follows: s t+1 =f(s t ,u t ); Among them, s t+1 The state of the dynamic system at time t+1 is represented by s. t u represents the state of the dynamic system at time t; t This represents the control command at time t.

4. The energy efficiency optimization task management method under the vehicle-road-cloud communication architecture according to claim 2, characterized in that, The expression for the reward function is as follows: Where r represents environmental reward; Indicates the engine's instantaneous fuel consumption; SoC ref denoted as the reference state of charge of the power battery; SoC(t) represents the state of charge of the power battery at time t; α and β represent the weighting coefficients of the corresponding terms.

5. An energy efficiency optimization task management system under a vehicle-road-cloud communication architecture, characterized in that, The energy efficiency optimization task management system under the vehicle-road-cloud communication architecture includes roadside equipment (RSE) and a cloud platform; wherein... The roadside equipment (RSE) is used to acquire historical speed data of several vehicles on the target road segment and the status of hybrid vehicles; based on the historical speed data of the vehicles on the target road segment, it generates representative driving conditions for the target road segment; and sends the representative driving conditions and the status of hybrid vehicles to the cloud platform. The generation process of the representative driving conditions specifically includes: Based on the historical speed data of several vehicles on the target road segment, the historical acceleration data of several vehicles are calculated; the historical speed data and the historical acceleration data of several vehicles on the target road segment are divided into several discrete intervals; the state probability transition matrix corresponding to each discrete interval is determined; based on the state probability transition matrix corresponding to each discrete interval, a representative driving condition of the target road segment is generated. The step of generating representative driving conditions for the target road segment based on the state probability transition matrix corresponding to each discrete interval specifically includes: Set the initial state corresponding to the driving condition; the initial state includes the speed and acceleration at the start time of the target road segment; randomly sample the state probability transition matrix to obtain the speed and acceleration at the next moment; determine whether the termination state corresponding to the driving condition has been reached; the termination state includes the speed at the end time of the target road segment and the total mileage corresponding to the driving condition; the total mileage corresponding to the driving condition is the mileage of the target road segment; if not, return to the step "randomly sample the state probability transition matrix to obtain the vehicle speed and vehicle acceleration at the next moment" until the termination state is reached to obtain the first driving condition; determine whether the first driving condition meets the feature value deviation requirement; if it does, determine the first driving condition as the representative driving condition of the target road segment; The cloud platform is used to execute the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture as described in any one of claims 1-4.

6. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture according to any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture as described in any one of claims 1-4.

8. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the energy efficiency optimization task management method under the vehicle-road-cloud communication architecture as described in any one of claims 1-4.

Images