Spectrum resource allocation method, device, equipment and storage medium for vehicle network

Abstract

The present application relates to a spectrum resource allocation method, apparatus, device and storage medium for a vehicle network, the method comprising: obtaining a first channel gain set and a first transmission power of each V2I link for each V2I link; allocating spectrum resource blocks to each V2I link according to the first channel gain set, the first transmission power and the resource block set; clustering a number of V2V links to obtain a V2V link cluster set; obtaining a second channel gain set between each V2V link and each V2I link, and allocating spectrum resource blocks to each V2V link according to the second channel gain set, the V2V link cluster set and each V2I link; obtaining status information of a number of V2V links in each V2V link cluster to which spectrum resource blocks have been allocated, inputting the status information into a trained transmission power allocation model, and obtaining the optimal transmission power of each V2V link, thereby reducing the computational complexity of spectrum resource allocation and improving the service quality of spectrum resource allocation.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a spectrum resource allocation method, device, equipment and storage medium for a vehicle network. Background Art

[0002] The vehicle network is a stable and high-speed data exchange network that can establish communication connections between vehicles with communication capabilities and between vehicles and surrounding infrastructure. Through the transmission of safety information and non-safety information within the vehicle network, the vehicle network can improve the road safety of millions of vehicles and enhance the driving experience, making daily travel safer and more convenient. Vehicle networks can be divided into vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), vehicle-to-pedestrian (V2P) and vehicle-to-Internet (V2N) according to the different connection objects within the network. All these connections are collectively referred to as vehicle-to-everything network (V2X).

[0003] In a cellular-based V2X vehicle network, limited, orthogonal spectrum resource blocks are allocated to cellular users or V2I users, and each cellular user or V2I user shares it with multiple V2V users based on D2D technology. This communication mode improves spectrum resource utilization and increases network efficiency and capacity. However, each spectrum resource block is shared between a cellular user or V2I user and multiple V2V users, and competition between cellular users or V2I users and multiple V2V users can cause huge interference. Therefore, effective spectrum resource allocation is one of the main challenges of cellular-based V2X vehicle networks.

[0004] The traditional spectrum allocation scheme for vehicle networks is completed in a centralized manner by the base station. The base station collects the channel state information of all links in the vehicle network and uses the optimization method to solve the channel allocation and power selection. However, due to the high mobility and rapid channel state changes in the vehicle network, it is very difficult to accurately estimate the channel state information of all links in the system. At the same time, frequent channel state information transmission will lead to high signaling load and delay. Summary of the invention

[0005] Based on this, the purpose of the present invention is to provide a spectrum resource allocation method, device, equipment and storage medium for a vehicle network, which can reduce the computational complexity of spectrum resource allocation and improve the service quality of spectrum resource allocation.

[0006] According to a first aspect of an embodiment of the present application, a spectrum resource allocation method for a vehicle network is provided, comprising the following steps:

[0007] Acquire a first channel gain set for each of the V2I links and a first transmit power for each of the V2I links;

[0008] Allocate spectrum resource blocks for each of the V2I links according to the first channel gain set, the first transmit power, and the resource block set, so that each of the V2I links occupies one spectrum resource block;

[0009] Clustering a plurality of the V2V links to obtain a V2V link cluster set;

[0010] Acquire a second channel gain set between each of the V2V links and each of the V2I links, and allocate spectrum resource blocks to each of the V2V links according to the second channel gain set, the V2V link cluster set, and each of the V2I links, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link;

[0011] The state information of several V2V links in each V2V link cluster of the allocated spectrum resource block is obtained, and the state information is input into a trained transmission power allocation model to obtain the optimal transmission power of each V2V link to maximize the channel capacity of the vehicle network.

[0012] According to a second aspect of an embodiment of the present application, a spectrum resource allocation device for a vehicle network is provided, including:

[0013] A channel gain set acquisition module, configured to acquire a first channel gain set for each of the V2I links and a first transmit power for each of the V2I links;

[0014] A first resource block allocation module, configured to allocate spectrum resource blocks to each of the V2I links according to the first channel gain set, the first transmit power and the resource block set, so that each of the V2I links occupies one spectrum resource block;

[0015] A link cluster set obtaining module, used for clustering a plurality of the V2V links to obtain a V2V link cluster set;

[0016] A second resource block allocation module is used to obtain a second channel gain set between each of the V2V links and each of the V2I links, and allocate spectrum resource blocks to each of the V2V links according to the second channel gain set, the V2V link cluster set and each of the V2I links, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link;

[0017] The transmission power acquisition module is used to obtain the status information of several V2V links in each V2V link cluster of the allocated spectrum resource block, input the status information into the trained transmission power allocation model, and obtain the optimal transmission power of each V2V link to maximize the channel capacity of the vehicle network.

[0018] According to a third aspect of an embodiment of the present application, a computer device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing a spectrum resource allocation method for a vehicle network as described in any one of the above items.

[0019] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the spectrum resource allocation method for a vehicle network as described in any one of the above items is implemented.

[0020] The embodiment of the present application obtains a first channel gain set and a first transmission power of each V2I link; allocates spectrum resource blocks to each V2I link according to the first channel gain set, the first transmission power and the resource block set, so that each V2I link occupies one spectrum resource block; clusters a plurality of V2V links to obtain a V2V link cluster set; obtains a second channel gain set between each V2V link and each V2I link, and allocates spectrum resource blocks to each V2V link according to the second channel gain set, the V2V link cluster set and each V2I link, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link; obtains status information of a plurality of V2V links in each V2V link cluster to which spectrum resource blocks have been allocated, inputs the status information into a trained transmission power allocation model, and obtains the optimal transmission power of each V2V link, so as to maximize the channel capacity of the vehicle network, thereby reducing the computational complexity of spectrum resource allocation and improving the service quality of spectrum resource allocation.

[0021] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application.

[0022] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A system model in an application environment of a spectrum resource allocation method for a vehicle network provided by an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a flow chart of a spectrum resource allocation method for a vehicle network provided in one embodiment of the present application;

[0025] Figure 3 A schematic diagram of a flow chart of step S20 of a method for allocating spectrum resources for a vehicle network provided in one embodiment of the present application;

[0026] Figure 4 A schematic diagram of a flow chart of step S30 of a spectrum resource allocation method for a vehicle network provided in one embodiment of the present application;

[0027] Figure 5 A flowchart of step S40 of a method for allocating spectrum resources for a vehicle network provided in one embodiment of the present application;

[0028] Figure 6 A schematic diagram of a flow chart of step S50 of a spectrum resource allocation method for a vehicle network provided in one embodiment of the present application;

[0029] Figure 7 A structural block diagram of a spectrum resource allocation device for a vehicle network provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0031] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0032] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms of "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0033] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0034] In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0035] Figure 1 The system model in the application environment of the spectrum resource allocation method of the vehicle network described in the present invention includes a cell centered on a single base station and a two-way road. In this system model, a plurality of V2I links and a plurality of V2V links are used to provide high-speed and reliable data information transmission services.

[0036] See also Figure 2 , which is a flow chart of a spectrum resource allocation method for a vehicle network provided by an embodiment of the present application. The spectrum resource allocation method for a vehicle network provided by an embodiment of the present application, wherein the vehicle network includes a base station, a plurality of V2I links, and a plurality of V2V links, comprises the following steps:

[0037] S10: Acquire a first channel gain set for each of the V2I links and a first transmit power for each of the V2I links.

[0038] In an embodiment of the present application, the vehicle network includes a base station, M V2I links and K V2V links, and the M V2I links and the K V2V links are marked by m∈{1, 2, ..., M} and k∈{1, 2, ..., K}, respectively. Each V2I link needs to be allocated a mutually orthogonal spectrum resource block when communicating, and the spectrum resource block is marked by f∈{1, 2, ..., F}.

[0039] The purpose of the embodiment of the present application is to maximize the channel capacity of the vehicle network, that is, to maximize the channel capacity of the V2I link and the V2V link, which is expressed as follows:

[0040]

[0041] in, represents the channel capacity when the mth V2I link uses the fth spectrum resource block, represents the channel capacity when the kth V2V link uses the fth spectrum resource block, where when the mth V2I link uses the fth spectrum resource block, ρ mf =1, otherwise 0. When the kth V2I link reuses the fth spectrum resource block, ρ kf =1, otherwise 0.

[0042] Considering the larger standard of signal-to-noise ratio, the channel capacity of the V2I link can be It is expressed as:

[0043]

[0044]

[0045] Where W is the bandwidth of each spectrum resource block and is a constant; is the signal-to-noise ratio of the mth V2I link when using the fth spectrum resource block; is the transmission power of the V2I link; g Bm [f] is the channel gain of the communication between the vehicle and the base station when the mth V2I link uses the fth spectrum resource block; is the transmission power of the kth V2V link when reusing the fth spectrum resource block, g kB [f] is the channel gain of the kth V2V link to the mth V2I link, ρ k [f] indicates whether the kth v2v link reuses the fth spectrum resource block, satisfying ∑ k ρ k [f]≤1, when the kth V2V link reuses the fth spectrum resource block, ρ k [f] is 1, otherwise it is 0; σ 2 represents the noise gain.

[0046] Channel capacity for V2I links Introducing the maximum transmission rate allowed for each V2V link satisfy Thus we can get:

[0047]

[0048] Further, based on some basic properties of logarithmic operations, the channel capacity of the V2I link can be maximized

[0049]

[0050] It is expressed as:

[0051]

[0052] Further, the above formula is split into two formulas, expressed as:

[0053]

[0054]

[0055] Therefore, in order to maximize the channel capacity of the V2I link and ensure the transmission rate of the V2I link, it is necessary to Maximum, and Minimum.

[0056] In the embodiment of the present application, the first channel gain of each V2I link is the channel gain of the communication between the vehicle and the base station when each V2I link uses any spectrum resource block, which can be expressed as a number of g Bm [f], f∈{1, 2, ..., F}, get all g Bm [f], the first channel gain set of each V2I link can be obtained. The first transmission power of each V2I link is the transmission power when the vehicle and the base station communicate in each V2I link, which is a fixed value and has nothing to do with which spectrum resource block is used. express.

[0057] S20: Allocate spectrum resource blocks to each of the V2I links according to the first channel gain set, the first transmit power, and the spectrum resource block set, so that each of the V2I links occupies one spectrum resource block.

[0058] In an embodiment of the present application, the spectrum resource block set includes F mutually orthogonal spectrum resource blocks, and each spectrum resource block is marked by f∈{1, 2, ..., F}. Considering that the channel gain of each V2I link in communication between the vehicle and the base station is different when using different spectrum resource blocks, that is, each first channel gain in the first channel gain set is different. According to the first channel gain set, the first transmission power and the spectrum resource block set, an optimal spectrum resource block is allocated to each V2I link to maximize the channel capacity of the V2I link, thereby ensuring the transmission rate of the V2I link.

[0059] S30: Clustering the plurality of V2V links to obtain a V2V link cluster set.

[0060] In an embodiment of the present application, K V2V links can reuse the spectrum resource blocks of M V2I links, thereby improving the utilization rate of spectrum resources. When allocating spectrum resource blocks to K V2V links, the K V2V links are first divided into multiple V2V link clusters, so that the interference between V2V links in each V2V link cluster is relatively minimized. Several V2V links in the same V2V link cluster can reuse the spectrum resource blocks of the same V2I link.

[0061] S40: Obtain a second channel gain set between each of the V2V links and each of the V2I links, and allocate spectrum resource blocks to each of the V2V links according to the second channel gain set, the V2V link cluster set, and each of the V2I links, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link.

[0062] In the embodiment of the present application, each second channel gain is the channel gain of a V2V link to a V2I link when a V2V link reuses the spectrum resource block of any V2I link, which can be expressed as g kB [f], where g kB [f] is the channel gain of the kth V2V link to the mth V2I link when the kth V2V link reuses the spectrum resource block of the mth V2I link. For f∈{1, 2, …, F}, obtain all g kB [f], a second channel gain set between each of the V2I links and each of the V2I links can be obtained. According to the second channel gain set, the V2V link cluster set and each of the V2I links, the V2V link cluster with the least interference to the V2I link reuses the spectrum resource block of the corresponding V2I link, thereby reducing the interference of the V2V link to the V2I link and maximizing the channel capacity of the V2I link.

[0063] S50: Obtain status information of several V2V links in each of the V2V link clusters of the allocated spectrum resource blocks, input the status information into a trained transmission power allocation model, and obtain the optimal transmission power of each of the V2V links to maximize the channel capacity of the vehicle network.

[0064] In the embodiment of the present application, in order to maximize the channel capacity of all V2V links, it is necessary to select the transmission power of each V2V link. The channel capacity maximization of the V2V link is expressed as:

[0065]

[0066]

[0067]

[0068] in, is the signal-to-noise ratio when the kth V2I link reuses the fth spectrum resource block, g kk′ [f] is the channel gain of the k′th V2V link to the kth V2V link, g mk [f] represents the channel gain of the mth V2I link to the kth V2V link, It represents the transmission power when the k′th V2V link reuses the fth spectrum resource block.

[0069] Before inputting the state information of several V2V links in each of the V2V link clusters of the allocated spectrum resource blocks into the trained transmission power allocation model, the embodiment of the present application also trains the transmission power allocation model. The transmission power allocation model is a multi-agent reinforcement learning model. The vehicle in each V2V link acts as an agent of the multi-agent reinforcement learning model. It selects an action based on the current state information obtained from the vehicle network environment, that is, selects a transmission power, and obtains a reward value. The reward value is used as feedback to adjust the next action of the agent, and the state information in the vehicle network environment is converted to the new state information. Repeat this process until the optimal transmission power of each agent can be determined.

[0070] Specifically, each agent includes an actor network and a critic network. The actor network receives the state information and outputs a value range of The transmit power of -100dBm is 0. The critic network receives the transmit power output by the actor network and outputs a Q value, where the Q value represents the quality of the transmit power selected by the actor network. The agent receives the reward value and obtains the next state information by reusing the spectrum resource block of the V2I link and using the output transmit power. The reward value consists of the channel capacity of the V2I link and the channel capacity of the V2V link, expressed as: in, represents the channel capacity of the V2I link, represents the channel capacity of the V2V link, λ m represents the weight coefficient of the channel capacity of the V2I link, λ k′ The weight coefficient representing the channel capacity of the V2V link.

[0071] For each agent’s actor network a=π(s|θ μ ) and the critic network Q(s, a|θ Q ), set the weight parameter θ of the actor network μ and the weight parameter θ of the critic networkQ , s is the state information received by the agent, and a is the transmission power selected by the agent. Since the neural network parameters are frequently updated while being used to calculate the gradients of the actor network and the critic network, the neural network learning process will be unstable. Therefore, two neural networks, Online Network and Target Network, are created for the actor network and the critic network respectively. The two Target Networks use the neural network parameters θ μ′ and θ Q′ Mapping the current state. Through the continuous interaction between the agent and the environment, the state, action, reward value, next state and other parameters are generated to slowly update the two networks. Among them, the weight parameter θ of the actor network μ The update of the critic network weight parameter θ is done by the chain rule. Q By updating the Bellman equation, the neural network parameters θ of the two Target Networks μ′ and θ Q′ Neural network parameters θ based on Online Network μ and θ Q Update using the soft replace method.

[0072] Specifically, through Calculate the Q value y of Online Critic Network and Target Critic Network respectively i .

[0073] Use the mean squared error loss function:

[0074]

[0075] Update all parameters of the Online Critic Network current network through the gradient back propagation of the neural network Q .

[0076] The parameters of the Online Actor Network are updated using a sampling strategy function:

[0077]

[0078] Similarly, all parameters θ of the current network of the Online Actor Network are updated through the gradient back propagation of the neural network μ .

[0079] After the Online Network is updated, use soft Replace to update the neural network parameters θ of the two Target Networks.μ′ and θ Q′ .

[0080] According to the embodiment of the present application, a first channel gain set and a first transmission power of each V2I link are obtained; spectrum resource blocks are allocated to each V2I link according to the first channel gain set, the first transmission power and the resource block set, so that each V2I link occupies one spectrum resource block; a plurality of V2V links are clustered to obtain a V2V link cluster set; a second channel gain set between each V2V link and each V2I link is obtained, and spectrum resource blocks are allocated to each V2V link according to the second channel gain set, the V2V link cluster set and each V2I link, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link; status information of a plurality of V2V links in each V2V link cluster to which spectrum resource blocks have been allocated is obtained, and the status information is input into a trained transmission power allocation model to obtain the optimal transmission power of each V2V link, so as to maximize the channel capacity of the vehicle network, thereby reducing the computational complexity of spectrum resource allocation and improving the service quality of spectrum resource allocation.

[0081] In an alternative embodiment, see Figure 3 The step S20 includes steps S21 to S24, which are specifically as follows:

[0082] S21: using the spectrum resource block set and the plurality of V2I links as the first vertex set and the second vertex set of a first weighted bipartite graph, respectively; wherein each vertex in the first vertex set of the first weighted bipartite graph is a spectrum resource block, and each vertex in the second vertex set of the first weighted bipartite graph is a V2I link;

[0083] S22: Connect the vertices of the first vertex set and the second vertex set of the first weighted bipartite graph one by one to obtain a plurality of edges of the first weighted bipartite graph;

[0084] S23: Calculate the weight of each edge of the first weighted bipartite graph according to the first channel gain set and the first transmit power;

[0085] S24: When the sum of the weights of all the edges of the first weighted bipartite graph is the largest, the spectrum resource blocks connected to each vertex in the second vertex set are used as the spectrum resource blocks occupied by each of the V2I links.

[0086] A bipartite graph, also known as a bipartite graph, is a special model in graph theory. Let G = (V, E) be an undirected graph. If the vertex V can be divided into two non-intersecting subsets (A, B), and the two vertices i and j associated with each edge (i, j) in the graph belong to these two different vertex sets (i in A, j in B), then the graph G is called a bipartite graph. The Hungarian algorithm is an algorithm that uses augmenting paths to solve the maximum matching problem of bipartite graphs. Starting from an unmatched point and taking an alternating path, if it passes through another unmatched point (the starting point is not counted), then this alternating path is called an augmenting path.

[0087] In an embodiment of the present application, a spectrum resource block set and M V2I links are respectively used as the first vertex set and the second vertex set of the first weighted bipartite graph, a vertex is selected from the first vertex set, i.e., a spectrum resource block, and a vertex is selected from the second vertex set, i.e., a V2I link, and the two selected vertices are connected, i.e., one V2I link uses one spectrum resource block, to obtain an edge of the first weighted bipartite graph, and the weight of this edge is calculated based on the first channel gain and transmission power of the selected V2I link when using the selected spectrum resource block.

[0088] Specifically, when the mth V2I link uses the fth spectrum resource block, the weight of the edge of the first weighted bipartite graph is Through the Hungarian algorithm, find the maximum sum of the weights of all edges of the first weighted bipartite graph, that is, At this time, the spectrum resource block connected to each V2I link in the first weighted bipartite graph is used as the spectrum resource block allocated to each V2I link.

[0089] In an alternative embodiment, see Figure 4 The step S30 includes steps S31 to S32, which are specifically as follows:

[0090] S31: Obtaining path losses of a plurality of the V2V links and the second channel gain set;

[0091] S32: Clustering the plurality of V2V links according to the path loss and the second channel gain set to obtain a V2V link cluster set.

[0092] In the embodiment of the present application, the maximum cut algorithm (Max N-cut algorithm) is used to traverse the path loss of all V2V links and the gain information g of the V2V link to the V2I link. Bm[f] All V2V links are divided into V2V link clusters with the same number of V2I links. Path loss refers to the attenuation of the average power of the received signal caused by the diffusion of radio wave energy as the transmission path increases when the radio signal is transmitted through a large-scale channel. The attenuation is related to the transmission distance. The greater the distance, the greater the attenuation.

[0093] In an alternative embodiment, see Figure 5 The step S40 includes steps S41 to S44, which are specifically as follows:

[0094] S41: using the V2V link cluster set and the plurality of V2I links as the first vertex set and the second vertex set of a second weighted bipartite graph, respectively; wherein each vertex in the first vertex set of the second weighted bipartite graph is a V2V link cluster, and each vertex in the second vertex set of the second weighted bipartite graph is a V2I link;

[0095] S42: Connect the vertices of the first vertex set and the second vertex set of the second weighted bipartite graph one by one to obtain a plurality of edges of the second weighted bipartite graph;

[0096] S43: Calculate the weight of each edge of the second weighted bipartite graph according to the second channel gain and the preset transmit power;

[0097] S44: When the sum of the weights of all the edges of the second weighted bipartite graph is minimum, a spectrum resource block occupied by a V2I link connected to each vertex in the first vertex set is used as a spectrum resource block of each of the V2V link clusters.

[0098] In an embodiment of the present application, a V2V link cluster set and M V2I links are respectively used as the first vertex set and the second vertex set of a second weighted bipartite graph, a vertex is selected from the first vertex set, i.e., a V2V link cluster, and a vertex is selected from the second vertex set, i.e., a V2I link, and the two selected vertices are connected, i.e., a V2V link cluster reuses a spectrum resource block of a V2I link, to obtain an edge of the second weighted bipartite graph, and the weight of this edge is calculated based on the second channel gain and preset power of the selected V2I link cluster when reusing a spectrum resource block of a V2I link.

[0099] Specifically, when the kth V2V link reuses the fth spectrum resource block corresponding to the mth V2I link, the weight of the edge of the second weighted bipartite graph is The preset power is expressed as is a fixed constant, indicating the maximum transmission power allowed for each V2V link. Through the Hungarian algorithm, we find the minimum sum of the weights of all edges of the second weighted bipartite graph, that is, At this time, the spectrum resource block of the V2I link reused by each V2V link cluster in the second weighted bipartite graph is used as the spectrum resource block allocated to each V2V link cluster.

[0100] In an optional embodiment, the status information of each V2V link includes the channel gains of several V2I links to the V2V link, the channel gains of the remaining V2V links to the V2V link, and the load information of the V2V link, see Figure 6 The step S50 includes steps S51 to S52, which are specifically as follows:

[0101] S51: converting the channel gains of the several V2I links to the V2V link, the channel gains of the remaining V2V links to the V2V link, and the load information of the V2V link into a first vector, a second vector, and a third vector, and performing vector splicing on the first vector, the second vector, and the third vector to obtain a state vector;

[0102] S52: Input the state vector into a trained power allocation model to obtain the optimal transmission power of each of the V2V links.

[0103] In the embodiment of the present application, the state vector of the state information conversion of the kth V2V link at time slot t is: The state vector By inputting into the trained power allocation model, the optimal transmission power of each V2V link can be obtained.

[0104] The following is an embodiment of the device of the present application, which can be used to execute the content of the method in Embodiment 1 of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the content of the method in Embodiment 1 of the present application.

[0105] See also Figure 7 , which shows a schematic diagram of the structure of a spectrum resource allocation device for a vehicle network provided in an embodiment of the present application. The spectrum resource allocation device 6 for a vehicle network provided in an embodiment of the present application includes:

[0106] A channel gain set acquisition module 61 is used to acquire a first channel gain set of each of the V2I links and a first transmit power of each of the V2I links;

[0107] A first resource block allocation module 62, configured to allocate spectrum resource blocks to each of the V2I links according to the first channel gain set, the first transmit power and the resource block set, so that each of the V2I links occupies one spectrum resource block;

[0108] A link cluster set obtaining module 63, configured to cluster a plurality of the V2V links to obtain a V2V link cluster set;

[0109] A second resource block allocation module 64 is configured to obtain a second channel gain set between each of the V2V links and each of the V2I links, and allocate spectrum resource blocks to each of the V2V links according to the second channel gain set, the V2V link cluster set, and each of the V2I links, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link;

[0110] The transmission power acquisition module 65 is used to obtain the status information of several V2V links in each V2V link cluster of the allocated spectrum resource block, input the status information into the trained transmission power allocation model, and obtain the optimal transmission power of each V2V link to maximize the channel capacity of the vehicle network.

[0111] According to the embodiment of the present application, a first channel gain set and a first transmission power of each V2I link are obtained; spectrum resource blocks are allocated to each V2I link according to the first channel gain set, the first transmission power and the resource block set, so that each V2I link occupies one spectrum resource block; a plurality of V2V links are clustered to obtain a V2V link cluster set; a second channel gain set between each V2V link and each V2I link is obtained, and spectrum resource blocks are allocated to each V2V link according to the second channel gain set, the V2V link cluster set and each V2I link, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link; status information of a plurality of V2V links in each V2V link cluster to which spectrum resource blocks have been allocated is obtained, and the status information is input into a trained transmission power allocation model to obtain the optimal transmission power of each V2V link, so as to maximize the channel capacity of the vehicle network, thereby reducing the computational complexity of spectrum resource allocation and improving the service quality of spectrum resource allocation.

[0112] In one embodiment of the present application, the first resource block allocation module 62 includes:

[0113] A first weighted bipartite graph construction unit is used to use the spectrum resource block set and the plurality of V2I links as a first vertex set and a second vertex set of a first weighted bipartite graph, respectively; wherein each vertex in the first vertex set of the first weighted bipartite graph is a spectrum resource block, and each vertex in the second vertex set of the first weighted bipartite graph is a V2I link;

[0114] A first edge obtaining unit, used for connecting vertices of the first vertex set and the second vertex set of the first weighted bipartite graph one by one to obtain a plurality of edges of the first weighted bipartite graph;

[0115] a first weight calculation unit, configured to calculate the weight of each edge of the first weighted bipartite graph according to the first channel gain set and the first transmit power;

[0116] The first spectrum resource block allocation unit is configured to use the spectrum resource block connected to each vertex in the second vertex set as the spectrum resource block occupied by each V2I link when the sum of the weights of all edges of the first weighted bipartite graph is maximum.

[0117] In one embodiment of the present application, the link cluster set obtaining module 63 includes:

[0118] A path loss acquisition unit, configured to acquire the path losses of a plurality of the V2V links and the second channel gain set;

[0119] The link clustering unit is used to cluster the plurality of V2V links according to the path loss and the second channel gain set to obtain a V2V link cluster set.

[0120] In one embodiment of the present application, the second resource block allocation module 64 includes:

[0121] A second weighted bipartite graph construction unit, configured to use the V2V link cluster set and the plurality of V2I links as a first vertex set and a second vertex set of a second weighted bipartite graph, respectively; wherein each vertex in the first vertex set of the second weighted bipartite graph is a V2V link cluster, and each vertex in the second vertex set of the second weighted bipartite graph is a V2I link;

[0122] A second edge obtaining unit, used for connecting vertices of the first vertex set and the second vertex set of the second weighted bipartite graph one by one to obtain a plurality of edges of the second weighted bipartite graph;

[0123] A second weight calculation unit, configured to calculate the weight of each edge of the second weighted bipartite graph according to the second channel gain and a preset transmit power;

[0124] The second spectrum resource block allocation unit is used to use the spectrum resource block occupied by a V2I link connected to each vertex in the first vertex set as the spectrum resource block of each V2V link cluster when the sum of weights of all edges of the second weighted bipartite graph is minimum.

[0125] In one embodiment of the present application, the transmission power obtaining module 65 includes:

[0126] a state vector obtaining unit, configured to convert the channel gains of the plurality of V2I links to the V2V link, the channel gains of the remaining V2V links to the V2V link, and the load information of the V2V link into a first vector, a second vector, and a third vector, and perform vector splicing on the first vector, the second vector, and the third vector to obtain a state vector;

[0127] A transmission power acquisition unit is used to input the state vector into a trained power allocation model to obtain the optimal transmission power of each of the V2V links to maximize the channel capacity of the vehicle network.

[0128] The present application also provides an electronic device, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps of the above embodiment.

[0129] The present application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method steps of the above-mentioned embodiment when executed by a processor.

[0130] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, and the present invention is also intended to include these modifications and modifications.

Claims

1. A spectrum resource allocation method for a vehicle network, wherein the vehicle network includes a base station, a plurality of V2I links, and a plurality of V2V links, characterized in that: The steps include: Acquire a first channel gain set for each of the V2I links and a first transmit power for each of the V2I links; Allocate spectrum resource blocks for each of the V2I links according to the first channel gain set, the first transmit power, and the resource block set, so that each of the V2I links occupies one spectrum resource block, thereby maximizing the channel capacity of the V2I link; Clustering a plurality of the V2V links to obtain a V2V link cluster set; Acquire a second channel gain set between each of the V2V links and each of the V2I links, and allocate spectrum resource blocks to each of the V2V links according to the second channel gain set, the V2V link cluster set, and each of the V2I links, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link, minimizes interference to the V2I link, and maximizes the channel capacity of the V2I link; Obtain status information of several V2V links in each V2V link cluster of the allocated spectrum resource block, input the status information into a trained transmission power allocation model, and obtain the optimal transmission power of each V2V link to maximize the channel capacity of the vehicle network; wherein the status information of each V2V link includes channel gains of several V2I links to the V2V link, channel gains of the remaining V2V links to the V2V link, and load information of the V2V link; convert the channel gains of the several V2I links to the V2V link, the channel gains of the remaining V2V links to the V2V link, and the load information of the V2V link into a first vector, a second vector, and a third vector, perform vector splicing on the first vector, the second vector, and the third vector to obtain a state vector; input the state vector into a trained power allocation model to obtain the optimal transmission power of each V2V link to maximize the channel capacity of the vehicle network.

2. The spectrum resource allocation method for a vehicle network according to claim 1, characterized in that: The step of allocating spectrum resource blocks to each of the V2I links according to the first channel gain set, the first transmit power, and the spectrum resource block set so that each of the V2I links occupies one spectrum resource block includes: The spectrum resource block set and the plurality of V2I links are respectively used as a first vertex set and a second vertex set of a first weighted bipartite graph; wherein each vertex in the first vertex set of the first weighted bipartite graph is a spectrum resource block, and each vertex in the second vertex set of the first weighted bipartite graph is a V2I link; Connecting vertices of the first vertex set and the second vertex set of the first weighted bipartite graph one by one to obtain a plurality of edges of the first weighted bipartite graph; Calculate the weight of each edge of the first weighted bipartite graph according to the first channel gain set and the first transmit power; When the sum of the weights of all the edges of the first weighted bipartite graph is the largest, the spectrum resource blocks connected to each vertex in the second vertex set are used as the spectrum resource blocks occupied by each of the V2I links.

3. The spectrum resource allocation method for a vehicle network according to claim 1, characterized in that: The step of obtaining a second channel gain set between each of the V2V links and each of the V2I links, and allocating a spectrum resource block to each of the V2V links according to the second channel gain set, the V2V link cluster set, and each of the V2I links, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link, comprises: The V2V link cluster set and the plurality of V2I links are respectively used as the first vertex set and the second vertex set of a second weighted bipartite graph; wherein each vertex in the first vertex set of the second weighted bipartite graph is a V2V link cluster, and each vertex in the second vertex set of the second weighted bipartite graph is a V2I link; Connecting vertices of the first vertex set and the second vertex set of the second weighted bipartite graph one by one to obtain a plurality of edges of the second weighted bipartite graph; Calculate the weight of each edge of the second weighted bipartite graph according to the second channel gain and the preset transmit power; When the sum of the weights of all the edges of the second weighted bipartite graph is the smallest, a spectrum resource block occupied by a V2I link connected to each vertex in the first vertex set is used as a spectrum resource block of each of the V2V link clusters.

4. The spectrum resource allocation method for a vehicle network according to claim 1, characterized in that: The step of clustering the plurality of V2V links to obtain a V2V link cluster set includes: Obtaining path losses of a plurality of the V2V links and the second channel gain set; According to the path loss and the second channel gain set, a plurality of the V2V links are clustered to obtain a V2V link cluster set.

5. A spectrum resource allocation device for a vehicle network, comprising: A channel gain set acquisition module, configured to acquire a first channel gain set for each V2I link and a first transmit power for each of the V2I links; A first resource block allocation module, configured to allocate spectrum resource blocks to each of the V2I links according to the first channel gain set, the first transmit power and the resource block set, so that each of the V2I links occupies one spectrum resource block, thereby maximizing the channel capacity of the V2I link; A link cluster set obtaining module, used for clustering a plurality of V2V links to obtain a V2V link cluster set; A second resource block allocation module is used to obtain a second channel gain set between each of the V2V links and each of the V2I links, and allocate spectrum resource blocks to each of the V2V links according to the second channel gain set, the V2V link cluster set and each of the V2I links, so that each V2V link cluster in the V2V link cluster set reuses a spectrum resource block of the V2I link, minimizes interference to the V2I link, and maximizes the channel capacity of the V2I link; A transmission power acquisition module is used to obtain the status information of several V2V links in each V2V link cluster of the allocated spectrum resource block, input the status information into a trained transmission power allocation model, and obtain the optimal transmission power of each V2V link to maximize the channel capacity of the vehicle network; wherein the status information of each V2V link includes the channel gains of several V2I links to the V2V link, the channel gains of the remaining V2V links to the V2V link, and the load information of the V2V link; convert the channel gains of the several V2I links to the V2V link, the channel gains of the remaining V2V links to the V2V link, and the load information of the V2V link into a first vector, a second vector, and a third vector, and vector splice the first vector, the second vector, and the third vector to obtain a state vector; input the state vector into a trained power allocation model to obtain the optimal transmission power of each V2V link to maximize the channel capacity of the vehicle network.

6. The spectrum resource allocation device for a vehicle network according to claim 5, wherein the first resource block allocation module comprises: A first weighted bipartite graph construction unit is used to use the spectrum resource block set and the plurality of V2I links as a first vertex set and a second vertex set of a first weighted bipartite graph, respectively; wherein each vertex in the first vertex set of the first weighted bipartite graph is a spectrum resource block, and each vertex in the second vertex set of the first weighted bipartite graph is a V2I link; A first edge obtaining unit, used for connecting vertices of the first vertex set and the second vertex set of the first weighted bipartite graph one by one to obtain a plurality of edges of the first weighted bipartite graph; a first weight calculation unit, configured to calculate the weight of each edge of the first weighted bipartite graph according to the first channel gain set and the first transmit power; The first spectrum resource block allocation unit is configured to use the spectrum resource block connected to each vertex in the second vertex set as the spectrum resource block occupied by each V2I link when the sum of the weights of all edges of the first weighted bipartite graph is maximum.

7. The spectrum resource allocation device for a vehicle network according to claim 5, wherein the second resource block allocation module comprises: A second weighted bipartite graph construction unit, configured to use the V2V link cluster set and the plurality of V2I links as a first vertex set and a second vertex set of a second weighted bipartite graph, respectively; wherein each vertex in the first vertex set of the second weighted bipartite graph is a V2V link cluster, and each vertex in the second vertex set of the second weighted bipartite graph is a V2I link; A second edge obtaining unit, used for connecting vertices of the first vertex set and the second vertex set of the second weighted bipartite graph one by one to obtain a plurality of edges of the second weighted bipartite graph; A second weight calculation unit, configured to calculate the weight of each edge of the second weighted bipartite graph according to the second channel gain and a preset transmit power; The second spectrum resource block allocation unit is used to use the spectrum resource block occupied by a V2I link connected to each vertex in the first vertex set as the spectrum resource block of each V2V link cluster when the sum of weights of all edges of the second weighted bipartite graph is minimum.

8. A computer device comprising: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 4 when executing the computer program.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images