Virtual-real cooperative communication scheduling method suitable for digital twin workshop

Abstract

The invention provides a virtual-real cooperative communication scheduling method suitable for a digital twin workshop. Comprising the following steps: (1) a virtual-real cooperative communication scheduling method oriented to the low-speed subnet of the digital twin workshop; and (2) a virtual-real cooperative communication scheduling method for the high-speed subnet of the digital twin workshop. According to the method, the multi-cycle path is optimized and selected through the DAG model, and the method has the advantages in the aspects of reducing data transmission delay and improving network efficiency. Besides, the real-time performance and reliability of transmission can be ensured in a complex network environment, so that the virtual model can reflect the change of the physical world in time, and the efficient operation of the digital twin workshop is ensured. Compared with the prior art, the method is obviously improved in the aspects of network congestion, data transmission real-time performance and system resource utilization rate, and the efficiency and reliability of virtual-real collaboration in the digital twin system are improved.

Description

Technical Field

[0001] The present invention belongs to the field of industrial wireless networks; in particular, it relates to a virtual-reality collaborative communication scheduling method suitable for a digital twin workshop. Background Art

[0002] Driven by the new generation of information technology, many countries have launched advanced development plans to achieve smart manufacturing, which rely on the interoperability, integration and fusion between the physical and virtual worlds in the manufacturing process. Smart manufacturing requires real-time data collection, analysis and application in the production process, which relies on highly accurate and reliable technical support. In this context, digital twin technology has emerged, which enables all aspects of the production process to be simulated and optimized in a virtual environment by creating an exact virtual copy of the physical entity. Data is the driving force of digital twins, and real-time data transmission is essential to ensure the effectiveness of digital twin systems.

[0003] As an important part of the digital twin system, the Industrial Wireless Network (IWN) is responsible for collecting data from the physical world and transmitting it to the virtual copy. In the field of IWN, there are several key technical standards, such as ISA100.11a, WirelessHART, and WIA-PA, which are essential for achieving efficient operation of the network. With the continuous expansion and deepening of application scenarios, IWN faces more stringent real-time transmission requirements and needs to respond to sensor data updates faster to ensure that the digital twin system can reflect the current status of the physical entity in a timely manner. In the industrial scenario of digital twins, sensors need to monitor the status of workshop elements and transmit data to the central control system in real time. For example, in an aircraft assembly workshop, by creating a virtual digital model of the aircraft, the assembly process can be simulated in a virtual environment, so as to identify and solve potential problems before actual production. By real-time monitoring of the assembly line based on multi-source, multi-dimensional data and fine-grained analysis, engineers can adjust strategies and methods in time to ensure the quality of aircraft assembly.

[0004] With the development of microelectronics and wireless communication technologies, sensors and actuators have been optimized in terms of cost, size and intelligence, and are widely used in industrial automation, smart cities and environmental monitoring. The standardization and interoperability of equipment have improved the seamless integration of equipment and systems, leading to a surge in the number of nodes, which generate a large amount of data that needs to be transmitted to the central control system in real time and periodically for analysis and decision-making. However, the surge in data may cause overload of certain nodes in the data link, increase the risk of network congestion and data delay, and pose a challenge to the stability and reliability of the network. At the same time, network scheduling is also more complex, requiring flexible processing of multi-cycle and multi-length data packets and providing effective routing for each node to ensure stable data transmission.

[0005] Digital twin technology plays a revolutionary role in smart manufacturing by accurately simulating and optimizing production processes in a virtual environment by collecting data from sensors in real time. Wireless technology, as the "nervous system" of digital twins, connects sensors throughout the smart factory. As more and more sensors are integrated into digital twin systems, wireless sensor networks must meet diverse requirements, especially in terms of low latency to maintain real-time synchronization between digital copies and physical entities. In order to meet the needs of real-time data transmission, many technologies have been proposed and applied. For example, OFDMA is considered to be an efficient multi-user wireless communication technology that can improve spectrum utilization by dividing subcarriers into multiple resource units (RUs) and allocating them to different users. TDMA is widely used in TT communication scenarios due to its high determinism, such as time-triggered Ethernet and time-sensitive networks, which are used in scenarios requiring high reliability and determinism.

[0006] However, with the increasing complexity of industrial scenarios, IWN faces more and more challenges, especially in the virtual-real collaboration of digital twin workshops, both low-speed subnets and high-speed subnets have placed extremely high demands on the real-time and reliability of the network. Although traditional TDMA and OFDMA scheduling methods can meet the needs of real-time communication in specific scenarios, their shortcomings in scalability, load balancing, and scheduling complexity limit their application in large-scale industrial workshops.

[0007] Traditional load balancing methods in low-speed subnets often fail to fully consider the multi-source communication flows in the network, causing some nodes to carry too much traffic and become a bottleneck for network performance. At the same time, although the random access method of OFDMA applied in high-speed subnets can improve the flexibility of multi-user access, it is easy to cause conflicts under high load conditions, resulting in increased communication delays and transmission uncertainty, making it difficult to meet the strict requirements of digital twin workshops for latency. In response to these problems, although the existing technology has also tried to improve system performance by improving the scheduling algorithm (such as the precise scheduling method based on SMT theory), these methods often have high computational complexity and cannot be effectively applied in large-scale, multi-node industrial environments. Summary of the invention

[0008] The purpose of the present invention is to provide a virtual-reality collaborative communication scheduling method suitable for a digital twin workshop.

[0009] The present invention is achieved through the following technical solutions:

[0010] The present invention relates to a virtual-real collaborative communication scheduling method suitable for a digital twin workshop, comprising: (1) a virtual-real collaborative communication scheduling method for a low-speed subnet of a digital twin workshop; (2) a virtual-real collaborative communication scheduling method for a high-speed subnet of a digital twin workshop.

[0011] Preferably, the specific steps of the method for scheduling virtual-real collaborative communication in a low-speed subnet of a digital twin workshop are as follows:

[0012] Step 1: Multi-source single sink network model

[0013] The present invention focuses on uplink data from low-speed terminal system nodes to gateways. The use of this unidirectional communication model can simplify the analysis process while retaining the generality of key communication challenges, because the uplink traffic is usually much higher than the downlink traffic due to the continuous transmission of sensor data. In addition, the digital twin system exhibits obvious asymmetric characteristics, that is, the data flow from the physical entity to the digital copy is continuous, while the control instructions from the digital copy to the physical entity are relatively few. Therefore, focusing on unidirectional links can effectively capture the main traffic characteristics in these networks. The present invention uses the DAG model to describe the multi-hop topology of the IWN. This model is chosen because it can effectively represent the unidirectional communication and hierarchical relationships between nodes in the network. In this model, the terminal system nodes are abstracted as vertices, and the reachability and communication direction between nodes are represented by directed edges;

[0014] Step 2: Optimize the algorithm

[0015] First, define the loss function to guide the search optimization process to minimize the error;

[0016] The evaluation function of the algorithm needs to measure the load balancing rate of each layer, and its design takes into account the difference between the actual load and the theoretical average load. Specifically, for each layer in the network, the difference between the actual load of the node and the theoretical average load of the layer is derived, and the square root of the sum of the squares of these differences is taken to obtain a comprehensive load balancing metric; this comprehensive load balancing metric will guide the algorithm to find the optimal path solution to achieve load balancing;

[0017] Taking the multi-hop topology as an example, starting from the gateway node, it is divided into the first layer to the fourth layer from top to bottom; let V layer represents the set of all nodes in a certain layer, τ LCM is the lowest common multiple of the sending cycles of all communication flows; let LayerNum be the total number of layers, |V layer | represents the number of all nodes in the level, node v k The actual load is v k.Load can be calculated after determining the path selection scheme; since the first and last layers have no forwarding and fixed load, these two layers are not considered in the calculation; according to the idea of ​​hierarchical load balancing, the difference between the actual load of a single node and the theoretical hierarchical average load is used as the load balancing metric, and the loss function is in the form of root mean square error, expressed as:

[0018]

[0019] Among them, V layer represents the set of all nodes in a certain layer, |V layer | represents the number of all nodes in the level, τ LCM is the least common multiple of all communication flow transmission periods, ò is the link transmission delay of the communication flow, LayerNum is the total number of layers, and node v k The actual load is v k .Load, which can be calculated after determining the path selection scheme;

[0020] Use heuristic algorithms to optimize the path so that the actual load of the node is close to the average load. Specifically, use the Aurora Optimization Algorithm, which is inspired by the aurora produced by the convergence of high-energy particles from the solar wind at the two poles of the earth. It simulates the movement of particles by analyzing the movement of high-energy particles and in-depth research on the basic principles of physics;

[0021] The routing problem faced in the present invention is defined as a multi-source single sink problem, and its core goal is to find the optimal path solution in the IWN to achieve efficient data aggregation, specifically: first, for each source node, the algorithm finds all the shortest paths with the same number of hops, and the set of paths constitutes the solution space basis of the network path selection solution; after constructing a path set for each source node, these sets are merged to construct the path selection solution space of the entire network; the design idea of ​​PLO is used to construct a PLO optimization mechanism for hierarchical load balancing to achieve network load balancing; wherein, constructing a PLO optimization mechanism for hierarchical load balancing includes:

[0022] Mapping of individuals to path selection schemes: In PLO, each individual represents a potential solution; in HLB-PLO, each individual is mapped to a path combination, that is, each high-energy particle represents a potential communication path selection scheme in the network.

[0023] Mapping of dimensions to communication flows: Each dimension in PLO can be mapped to the path selection of each communication flow in HLB-PLO; in this way, the optimization objective of each dimension is associated with the path selection of the communication flow.

[0024] Mapping of fitness function: The fitness function in PLO needs to be redefined to adapt to the scenario-based objectives; In HLB-PLO, the fitness function is set to the HLB loss function that measures the load balancing performance of the path selection scheme.

[0025] Mapping of optimization objectives: The goal of PLO is to find the individual with the best fitness, while the goal in HLB-PLO is to find the path selection solution with the smallest HLB loss function value.

[0026] The optimization algorithm is executed in the solution space, which not only involves the search efficiency of the algorithm, but also requires the algorithm to accurately evaluate the performance of each path selection scheme. After overall optimization, the path selection scheme with the maximum fitness (i.e., the lowest HLB loss) is finally selected.

[0027] Preferably, the specific steps of the method for scheduling virtual-real collaborative communication of high-speed subnet for digital twin workshops are as follows:

[0028] Step 1: OFDMA network model

[0029] In order to achieve real-time and deterministic transmission, the present invention adopts a star topology, in which a group of terminal nodes are wirelessly connected to a base station; the communication system adopts TDMA to achieve deterministic medium access, in which time is divided into time slots (such as TTI);

[0030] The system achieves simultaneous stream transmission by allocating adjacent RUs to each terminal node, and each RU contains an equal number of data subcarriers; consider a system containing a group of TT streams, denoted as F, and assume that the transmission of each TT stream only requires one TTI; Figure 3 As shown, TT flow f i ∈F is provided by the terminal device ED i With period P i It is generated periodically, and its initial generation time is G i Then for this flow, from the set {1,2,...,N RU}, in order to maximize the utilization of frequency domain resources, the number of allocated RUs (denoted as RL i ) is set to support f i The minimum value required;

[0031] Step 2: TTI-RU constraint model

[0032] The present invention uses integer programming based on TTI-RU to construct a scheduling constraint model, called TTI-RU-IP; specifically, the OFDMA-based time-triggered network O i and RU i Constraints, where O i Represents the communication flow f i∈F’s initial sending time, RU i Assigned to f i ∈F, the smallest index among all RUs. Since the time-triggered flow is generated and sent periodically, the present invention only focuses on the scheduling strategy within its initial period;

[0033] The scheduling constraint model includes:

[0034] Constraint 1: Delay constraint: Each flow should be transmitted immediately after being generated, and its corresponding time window should not exceed its period, which can be expressed by the following formal expression:

[0035]

[0036] Constraint 2: RU continuity constraint: Each flow should be allocated RU from the set, expressed by the following constraint:

[0037]

[0038] Constraint 3: TTI-RU non-conflict constraint: Once any two flows and are assigned to the same RU, the TTIs they occupy during transmission must not overlap. The following constraints are derived to express this:

[0039]

[0040] Where G(P i ,P j ) indicates P i and P j The greatest common divisor of .

[0041] The present invention proposes a hierarchical load balancing routing algorithm for the virtual-real collaboration of low-speed data in digital twin workshops, which mainly optimizes multi-cycle communication flows by establishing a directed acyclic graph (DAG) model. The Polar Lights Optimization (PLO) algorithm is used to achieve global load balancing and avoid the problem of node overload. This method ensures the stability of data transmission in the low-speed subnet and improves the real-time response capability of the system. For the virtual-real collaboration of high-speed data in digital twin workshops, the present invention proposes a TT scheduling strategy based on OFDMA. This strategy optimizes resource allocation and ensures low-latency and conflict-free transmission by establishing a constraint model based on the Transmission Time Interval (TTI) and RU.

[0042] The present invention has the following advantages:

[0043] (1) The present invention improves the performance of virtual-real collaborative communication through load balancing and path optimization in the low-speed subnet. PLO realizes hierarchical load balancing, ensures balanced load distribution of each node in the network, avoids the network bottleneck phenomenon that occurs in traditional methods, and thus improves the overall stability of the system.

[0044] (2) The present invention optimizes and selects multi-cycle paths through the DAG model, which has advantages in reducing data transmission delay and improving network efficiency. In addition, the present invention can ensure the real-time and reliability of transmission in a complex network environment, so that the virtual model can reflect the changes in the physical world in a timely manner, ensuring the efficient operation of the digital twin workshop. Compared with traditional technologies, the present invention shows significant improvements in network congestion, real-time data transmission, and system resource utilization, improving the efficiency and reliability of virtual-real collaboration in digital twin systems.

[0045] (3) The present invention proposes a hierarchical load balancing routing algorithm for the problem of virtual-real collaborative transmission in low-speed subnets, mainly by establishing a DAG model to optimize multi-cycle communication flows. PLO is used to achieve global load balancing to avoid node overload problems. For the problem of virtual-real collaborative transmission in high-speed subnets, the present invention proposes a TT scheduling strategy based on OFDMA. This strategy optimizes resource allocation by establishing a constraint model based on TTI and RU to ensure low-latency and conflict-free transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a diagram of the mapping principle involved in the method of the present invention;

[0047] Figure 2 It is the principle diagram of the method of the present invention;

[0048] Figure 3 It is the PLO sub-flow chart of the present invention;

[0049] Figure 4 It is a diagram showing the topology structure and scheduling strategy;

[0050] Figure 5 This is a typical scene diagram of a digital twin workshop. DETAILED DESCRIPTION

[0051] The present invention is described in detail below in conjunction with specific embodiments. It should be noted that the following embodiments are only further descriptions of the present invention, but the protection scope of the present invention is not limited to the following embodiments.

[0052] Example 1

[0053] This embodiment involves a digital twin system in a manufacturing workshop, where the low-speed subnet is responsible for monitoring and reporting the real-time status of each device (such as temperature, humidity, vibration, etc.). In this example, the sensor nodes in the workshop are densely distributed, and the generated sensor data needs to be uploaded to the central control system for real-time updating of the digital twin model. Traditional scheduling methods will cause network congestion and transmission delays when the node load increases, affecting real-time performance.

[0054] The present invention achieves global load balancing by constructing a DAG model and applying HLB-PLO in a low-speed subnet to prevent certain nodes from becoming network bottlenecks due to traffic overload. The algorithm is used to optimize the communication path of the nodes to balance the data traffic of multi-source sensors and reasonably distribute the load to the entire network. Figure 2 As shown, the specific steps are as follows:

[0055] Step 1: Multi-source single sink network model

[0056] The present invention focuses on uplink data from low-speed end system nodes to gateways. The use of this unidirectional communication model can simplify the analysis process while retaining the generality of key communication challenges, because uplink traffic is usually much higher than downlink traffic due to the continuous transmission of sensor data. In addition, digital twin systems exhibit obvious asymmetric characteristics, that is, the data flow from physical entities to digital copies is continuous, while the control instructions from digital copies to physical entities are relatively few. Therefore, focusing on unidirectional links can effectively capture the main traffic characteristics in these networks. The present invention uses the DAG model to describe the multi-hop topology of IWN, see Figure 1 As shown in Figure 2, this model is chosen because it can effectively represent unidirectional communication and hierarchical relationships between nodes in the network. In this model, the end system nodes are abstracted as vertices, and the reachability and communication direction between nodes are represented by directed edges.

[0057] Step 2: Optimize the algorithm

[0058] First, define the loss function to guide the search optimization process to minimize the error;

[0059] The evaluation function of the algorithm needs to measure the load balancing rate of each layer, and its design takes into account the difference between the actual load and the theoretical average load. Specifically, for each layer in the network, the difference between the actual load of the node and the theoretical average load of the layer is derived, and the square root of the sum of the squares of these differences is taken to obtain a comprehensive load balancing metric; this comprehensive load balancing metric will guide the algorithm to find the optimal path solution to achieve load balancing;

[0060] by Figure 1 For example, starting from the gateway node, it is divided into the first layer to the fourth layer from top to bottom; let V layerrepresents the set of all nodes in a certain layer, τ LCM is the lowest common multiple of the sending cycles of all communication flows; let LayerNum be the total number of layers, |V layer | represents the number of all nodes in the level, node v k The actual load is v k .Load can be calculated after determining the path selection scheme; since the first and last layers have no forwarding and fixed load, these two layers are not considered in the calculation; according to the idea of ​​hierarchical load balancing, the difference between the actual load of a single node and the theoretical hierarchical average load is used as the load balancing metric, and the loss function is in the form of root mean square error, expressed as:

[0061]

[0062] Among them, V layer represents the set of all nodes in a certain layer, |V layer | represents the number of all nodes in the level, τ LCM is the least common multiple of all communication flow transmission periods, ò is the link transmission delay of the communication flow, LayerNum is the total number of layers, and node v k The actual load is v k .Load, which can be calculated after determining the path selection scheme;

[0063] Use heuristic algorithms to optimize the path so that the actual load of the node is close to the average load. Specifically, use the Aurora Optimization Algorithm, which is inspired by the aurora produced by the convergence of high-energy particles from the solar wind at the two poles of the earth. It simulates the movement of particles by analyzing the movement of high-energy particles and in-depth research on the basic principles of physics;

[0064] The routing problem faced in the present invention is defined as a multi-source single sink problem. Its core goal is to find the optimal path solution in the IWN to achieve efficient data aggregation. Specifically, for each source node, the algorithm finds all the shortest paths with the same number of hops. The set of paths constitutes the solution space basis of the network path selection solution. After constructing the path set for each source node, these sets are merged to construct the path selection solution space of the entire network. The design idea of ​​PLO is used to construct a PLO optimization mechanism for hierarchical load balancing, see Figure 3 As shown in the figure, network load balancing is achieved; wherein, the PLO optimization mechanism for hierarchical load balancing is constructed including:

[0065] Mapping of individuals to path selection schemes: In PLO, each individual represents a potential solution; in HLB-PLO, each individual is mapped to a path combination, that is, each high-energy particle represents a potential communication path selection scheme in the network.

[0066] Mapping of dimensions to communication flows: Each dimension in PLO can be mapped to the path selection of each communication flow in HLB-PLO; in this way, the optimization objective of each dimension is associated with the path selection of the communication flow.

[0067] Mapping of fitness function: The fitness function in PLO needs to be redefined to adapt to the scenario-based objectives; In HLB-PLO, the fitness function is set to the HLB loss function that measures the load balancing performance of the path selection scheme.

[0068] Mapping of optimization objectives: The goal of PLO is to find the individual with the best fitness, while the goal in HLB-PLO is to find the path selection solution with the smallest HLB loss function value.

[0069] The optimization algorithm is executed in the solution space, which not only involves the search efficiency of the algorithm, but also requires the algorithm to accurately evaluate the performance of each path selection scheme. After overall optimization, the path selection scheme with the maximum fitness (i.e., the lowest HLB loss) is finally selected.

[0070] Example 2

[0071] This embodiment involves that in the same aviation manufacturing workshop, the high-speed subnet is mainly responsible for the transmission of complex data streams (such as quality inspection and equipment operation instructions), which have low latency and high bandwidth requirements. In this network environment, the traditional OFDMA random access method is difficult to avoid data conflicts in high-load scenarios, and the transmission delay is unstable, which affects the real-time transmission of key data.

[0072] The OFDMA-based TT scheduling strategy of this embodiment is applied in the high-speed subnet. Through the constraint optimization of TTI and RU, the solution realizes the reasonable allocation of resources and ensures conflict-free low-latency transmission. The specific steps are as follows:

[0073] Step 1: OFDMA network model

[0074] In order to achieve real-time and deterministic transmission, the present invention adopts a star topology, in which a group of terminal nodes are wirelessly connected to a base station; the communication system adopts TDMA to achieve deterministic medium access, in which time is divided into time slots (such as TTI);

[0075] The system achieves simultaneous stream transmission by allocating adjacent RUs to each terminal node, and each RU contains an equal number of data subcarriers; consider a system containing a group of TT streams, denoted as F, and assume that the transmission of each TT stream only requires one TTI; Figure 4 As shown, TT flow f i ∈F is provided by the terminal device ED i With period P iIt is generated periodically, and its initial generation time is G i Then for this flow, from the set {1,2,...,N RU}, in order to maximize the utilization of frequency domain resources, the number of allocated RUs (denoted as RL i ) is set to support f i The minimum value required;

[0076] Step 2: TTI-RU constraint model

[0077] The present invention uses integer programming based on TTI-RU to construct a scheduling constraint model, called TTI-RU-IP; specifically, the OFDMA-based time-triggered network O i and RU i Constraints, where O i Represents the communication flow f i ∈F’s initial sending time, RU i Assigned to f i ∈F, the smallest index among all RUs. Since the time-triggered flow is generated and sent periodically, the present invention only focuses on the scheduling strategy within its initial period;

[0078] The scheduling constraint model includes:

[0079] Constraint 1: Delay constraint: Each flow should be transmitted immediately after being generated, and its corresponding time window should not exceed its period, which can be expressed by the following formal expression:

[0080]

[0081] Constraint 2: RU continuity constraint: Each flow should be allocated RU from the set, expressed by the following constraint:

[0082]

[0083] Constraint 3: TTI-RU non-conflict constraint: Once any two flows and are assigned to the same RU, the TTIs they occupy during transmission must not overlap. The following constraints are derived to express this:

[0084]

[0085] Where G(P i ,P j ) indicates P i and P j The greatest common divisor of .

[0086] Experimental results show that the present invention improves the performance of virtual-reality collaborative communication through a time-triggered scheduling strategy based on OFDMA in a high-speed subnet. Through the joint optimization of TTI and RU, the present invention can effectively reduce the end-to-end delay of data transmission and increase the scheduling scale. The experiment verified the scheduling method under the joint optimization of TTI and RU, which showed lower delay and higher scheduling efficiency compared with the traditional scheme. The present invention maintains good real-time performance and high throughput, ensures the efficiency and reliability of virtual-reality collaborative communication, solves the problems of insufficient real-time responsiveness and network stability in the prior art, and improves the overall efficiency of virtual-reality collaboration in the digital twin workshop.

[0087] The production factors such as people, machines and objects in the digital twin workshop are interconnected through the network and applied to equipment monitoring, workshop management and real-time transmission of production status data. Figure 5 For low-speed transmission, the present invention balances the low-speed subnet load by scheduling routing resources. For high-speed transmission, the present invention uses TTI-RU joint optimization scheduling to schedule time-frequency resources to improve the transmission effect of high-speed subnet.

[0088] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art may make various modifications or variations within the scope of the claims, which will not affect the essence of the present invention.

Claims

1. A virtual-reality collaborative communication scheduling method suitable for a digital twin workshop, characterized in that: include: (1) Virtual-real collaborative communication scheduling method for low-speed subnet of digital twin workshop; (2) Virtual-real collaborative communication scheduling method for high-speed subnet of digital twin workshop.

2. The virtual-reality collaborative communication scheduling method applicable to a digital twin workshop according to claim 1, characterized in that: The specific steps of the virtual-real collaborative communication scheduling method for low-speed subnet of digital twin workshop are as follows: Step 1: Multi-source single sink network model The DAG model is used to describe the multi-hop topology of IWN. In this model, the end system nodes are abstracted as vertices, and the reachability and communication direction between nodes are represented by directed edges. Step 2: Optimize the algorithm First, define the loss function to guide the search optimization process to minimize the error; For each layer in the network, the difference between the actual node load and the theoretical average load is derived, and the square root of the sum of the squares of the differences is taken to obtain a comprehensive load balancing metric. This comprehensive load balancing metric will guide the algorithm to find the optimal path solution to achieve load balancing, specifically: The difference between the actual load of a single node and the theoretical average load of the level is used as the load balancing metric, and the loss function is in the form of root mean square error, expressed as: Among them, V layer represents the set of all nodes in a certain layer, |V layer | represents the number of all nodes in the level, τ LCM is the least common multiple of all communication flow transmission periods, ò is the link transmission delay of the communication flow, LayerNum is the total number of layers, and node v k The actual load is v k .Load, which can be calculated after determining the path selection scheme; Use heuristic algorithms to optimize the path so that the actual load of the node is close to the average load. Specifically, the Aurora optimization algorithm is used to simulate particle motion by analyzing the motion of high-energy particles and deeply studying the basic principles of physics; Find the optimal path solution in IWN to achieve efficient data aggregation. Specifically, first, for each source node, the algorithm finds all the shortest paths with the same number of hops, and the set of paths constitutes the solution space basis of the network path selection solution; after constructing the path set for each source node, these sets are merged to construct the path selection solution space of the entire network; use the design idea of ​​PLO to construct a PLO optimization mechanism for hierarchical load balancing to achieve network load balancing; among them, constructing a PLO optimization mechanism for hierarchical load balancing includes: Mapping of individuals to path selection solutions: In PLO, each individual represents a potential solution; Mapping of dimensions to communication flows: Each dimension in PLO can be mapped to the path selection of each communication flow in HLB-PLO; Mapping of fitness function: The fitness function in PLO needs to be redefined to adapt to the scenario-based objectives; Mapping of optimization objectives: The goal of PLO is to find the individual with the best fitness, while the goal in HLB-PLO is to find the path selection solution with the smallest HLB loss function value.

3. The virtual-reality collaborative communication scheduling method applicable to a digital twin workshop according to claim 1, characterized in that: The specific steps of the virtual-real collaborative communication scheduling method for the digital twin workshop high-speed subnet are as follows: Step 1: OFDMA network model It uses a star topology, where a set of terminal nodes are wirelessly connected to a base station. The communication system uses TDMA, where time is divided into time slots. The system consists of a set of TT flows, denoted as F. The transmission of each TT flow only requires one time slot. i ∈F is provided by the terminal device ED i With period P i It is generated periodically, and its initial generation time is G i ; The system achieves simultaneous streaming by allocating adjacent RUs to each terminal node, each RU containing an equal number of data subcarriers; from the set {1,2,...,N RU }, the number of RUs allocated is set to support f i The minimum value required is denoted as RL i ; Step 2: TTI-RU constraint model Based on TTI-RU, a scheduling constraint model called TTI-RU-IP is constructed using integer programming. i and RU i Constraints, where O i Represents the communication flow f i ∈F’s initial sending time, RU i Assigned to f i The smallest index among all RUs of ∈F; The scheduling constraint model includes: Constraint 1: Delay constraint: Each flow should be transmitted immediately after being generated, and its corresponding time window should not exceed its period, which can be expressed by the following formal expression: Constraint 2: RU continuity constraint: Each flow should be allocated RU from the set, expressed by the following constraint: Constraint 3: TTI-RU non-conflict constraint: Once any two flows and are assigned to the same RU, the TTIs they occupy during transmission must not overlap. The following constraints are derived to express this: Where G(P i ,P j ) indicates P i and P j The greatest common divisor of .

Images