TSN cross-domain traffic semi-distributed scheduling method based on two-color cooperative bat algorithm

Abstract

The application belongs to the technical field of wireless communication, and particularly relates to a TSN cross-domain traffic semi-distributed scheduling method based on a double-color cooperative bat algorithm. In the global TSN network, an intra-domain scheduler is arranged in each local TSN network. Each intra-domain scheduler collects and reports the traffic transmission demand in the corresponding local TSN network. A cross-domain coordinator is arranged in the global TSN network, which is used to collect the traffic transmission demand in the local TSN network reported by each intra-domain scheduler, obtain a traffic set and issue the traffic set. After receiving the traffic set, the intra-domain scheduler calculates a promised delay through an intra-domain traffic scheduling method and reports the promised delay. After receiving the calculated promised delay, the cross-domain coordinator generates an inter-domain scheduling strategy through an inter-domain routing selection method and issues the inter-domain scheduling strategy. The double-color cooperative bat algorithm is used for solving, so that the global optimal solution of the traffic scheduling in the local TSN network and the path selection of the local TSN network is obtained, so as to improve the scheduling efficiency of the global TSN traffic.

Description

Technical Field

[0001] This invention belongs to the field of wireless communication technology, specifically relating to a semi-distributed scheduling method for cross-domain traffic of TSN based on the dual-color cooperative bat algorithm. Background Technology

[0002] With the rapid development of Industry 4.0, smart manufacturing, and the Internet of Things (IoT), Time-Sensitive Networking (TSN), as a key technology for achieving efficient, reliable, and real-time communication, has been widely used in industrial automation, smart grids, and intelligent transportation. TSN networks, through precise time synchronization and traffic scheduling mechanisms, ensure low-latency and low-jitter transmission of data packets, meeting the stringent time-sensitivity requirements of various services.

[0003] However, in practical applications, TSN networks often face the challenge of cross-domain traffic scheduling. Because most currently built TSN networks are in a closed state with limited information exchange, it is difficult for various local TSN networks to be interconnected, thus hindering the provision of end-to-end transmission guarantees for wide-area services. To overcome this bottleneck, cross-domain traffic scheduling technology for TSNs has emerged as a core technology for solving this problem.

[0004] While some existing technical solutions have attempted to address the issues of TSN network time synchronization and traffic scheduling, current TSN cross-domain traffic scheduling technologies primarily face a key challenge: how to generate multi-domain integrated gating list configuration information to enhance the globality of intra-domain network scheduling. Solving this problem is crucial for achieving optimized TSN cross-domain traffic scheduling. Summary of the Invention

[0005] In view of this, the present invention provides a semi-distributed scheduling method for cross-domain traffic of TSN based on the dual-color cooperative bat algorithm, so as to solve the technical problem in the prior art that it is impossible to generate multi-domain fusion gating list configuration information to enhance the globality of intra-domain network scheduling.

[0006] To achieve the above objectives, this application adopts the following approach:

[0007] A semi-distributed scheduling method for cross-domain traffic of TSN based on the two-color cooperative bat algorithm includes the following steps:

[0008] S10. Deploy an intra-domain scheduler in each local TSN network within the global TSN network scope. Each intra-domain scheduler is responsible for traffic scheduling within its corresponding local TSN network. Each intra-domain scheduler collects traffic transmission requirements within its corresponding local TSN network and reports the traffic transmission requirements within the local TSN network.

[0009] S20. Set up a cross-domain coordinator in the global TSN network. The cross-domain coordinator is communicatively connected to each of the intra-domain schedulers. The cross-domain coordinator is responsible for the path selection of each of the local TSN networks. The cross-domain coordinator summarizes the traffic transmission requirements in the local TSN network reported by each intra-domain scheduler to obtain a traffic set, and sends the traffic set to each of the intra-domain schedulers.

[0010] S30. After receiving the traffic set, each intra-domain scheduler calculates the committed delay using the intra-domain traffic scheduling method and reports the calculated committed delay to the cross-domain coordinator.

[0011] S40. After receiving the calculated promised delay, the cross-domain coordinator generates an inter-domain scheduling policy through an inter-domain routing method and distributes the inter-domain scheduling policy to each intra-domain scheduler. The intra-domain scheduler performs distributed scheduling of the allocated traffic among intra-domain nodes and links according to the received inter-domain scheduling policy.

[0012] S50. The server in the domain scheduler performs joint optimization of traffic scheduling and path selection in the local TSN network. The two-color cooperative bat algorithm is used to solve the problem and obtain the global optimal solution for traffic scheduling and path selection in the local TSN network, so as to improve the scheduling efficiency of global TSN traffic.

[0013] Preferably, the intra-domain traffic scheduling method includes the following steps:

[0014] S31. Define the local TSN network topology as a directed graph G = (V, E), where V represents the set of nodes and E represents the set of links. The set of nodes V includes internal nodes v. in and cross-domain node v e The flow set is F, and each flow f in the flow set F i Represented as:

[0015] f i =(T i D i ,L i ,st i ,des i )

[0016] Among them, T i D represents the period of this flow. i The data frames that make up this traffic, L i st is the deadline for this traffic. i ,des i These are the source and destination nodes of the traffic, respectively.

[0017] S32. The traffic transmission order constraint includes, for the same link, ensuring that the transmission time of the first frame is non-negative, and that each frame is transmitted in chronological order:

[0018]

[0019] in, Describes each flow f in the flow set F. i The kth frame on link e This indicates GCL's closing time. Indicates the opening time of the GCL, where i, e, and k are all indices;

[0020] S33. The frame collision constraint includes the requirement that link resources should be exclusively occupied by the current traffic within the same transmission time slot; otherwise, collisions will occur between different traffic streams.

[0021]

[0022] Among them, T i and T j f i and f j The corresponding flow period, where m and n are non-negative integers;

[0023] S34. The intra-domain path constraints include the order in which local TSN network traffic is transmitted within the topology according to the links:

[0024]

[0025] Among them, e ab ,e bc ∈E, e ab ,e bc For any adjacent links in the link set E;

[0026] S35. The cutoff time constraints for each flow include ensuring that the end-to-end delay of the flow does not exceed its cutoff time:

[0027]

[0028] Among them, L i st is the deadline for this traffic. i For the source node of this traffic, des i The destination node for this traffic. This indicates the opening time of GCL. Indicates the closing time of GCL;

[0029] S36. The objective function for traffic scheduling within the defined domain, i.e., minimizing the sum of the times required for each flow to reach its destination node, includes:

[0030]

[0031] Among them, f i For each flow in the flow set F', H1 represents objective function 1.

[0032] Preferably, the inter-domain routing method includes the following steps:

[0033] S41. Let the network topology covering multiple local TSN networks be G' =<D,E> D represents the set of local TSN networks in the network, E represents the set of links, and the aggregate of traffic reported by all local TSN networks is F'. The optimal transmission path set R for each traffic flow between domains is calculated. Each flow f in the traffic set F' is... i Represented as:

[0034] f i =(P i U i ,L i ,st i ,des i )

[0035] Among them, P i For each domain, the promised lower bound of the flow's latency, U i For each domain, the upper bound of the latency commitment for this flow, L i The deadline for this stream, st i ,des i These are the source and destination nodes of the stream, respectively.

[0036] S42. The inter-domain path constraint includes flow f in each flow of the flow set F'. i Path R i It should be st i Starting from the point des i End point:

[0037]

[0038] Where R is the set of optimal transmission paths for each traffic flow between domains, R i For each traffic flow, the optimal transmission path between domains, st i For the source node of this stream, des i For the destination node of this flow, d a and d b For any two adjacent fields;

[0039] S43. Under the aforementioned flow cutoff time constraint, the TSN flow rate f i The end-to-end delay consists of intra-domain transmission delay and inter-domain link delay, and the delay does not exceed its specified deadline:

[0040]

[0041] Among them, f i For each flow in the flow set F' For flow f i The lower bound of the delay commitment in the d-domain, L i This is the deadline for the traffic flow;

[0042] S44. The objective function for inter-domain traffic routing selection is:

[0043]

[0044] Where H2 represents objective function 2. For flow f i Lower bound of the delay commitment in the d-domain For flow f i The upper bound of the delay commitment within the d domain.

[0045] Preferably, the two-color cooperative bat algorithm includes the following steps:

[0046] S51. Divide M bats into U black bats and W gray bats. The black bats are responsible for intra-domain traffic scheduling, and the gray bats are responsible for inter-domain routing selection.

[0047] S52. Initial bat positions: Discretize the bat positions in a given space to form a set of solutions. The bats are randomly distributed in the space, and the initial positions of the bats are:

[0048]

[0049] Where, vector This represents the initial position of the μ / ωth bat;

[0050] S53. A real-number encoding strategy is adopted, using vector information to represent each individual bat, and the vector... Ordinalization based on element size yields The priority order for obtaining individual bat location information:

[0051]

[0052] S54. Within each supercycle t, each bat performs a foraging process, updating the speed and position of each bat. By iteratively updating the speed and position of the bats, the global optimal solution is sought. The update of speed and position is divided into three stages: independent update, linked update, and local search.

[0053] Preferably, the algorithm for independent updates is as follows:

[0054]

[0055] in, Let μ be the flight speed of the μ / ωth black / gray bat at time t. Let f be the flight speed of the μ / ωth black / gray bat at time t-1, and rand be a random factor generated by the Chebyshev mapping, where rand∈(0,1). μ / ω For pulse frequency, Let be the independently updated position of the black / gray bat at time t, ∈ be the mutation weight, and C(0,1) be a random number generated by the Cauchy probability distribution with a scaling parameter of t=1. The inertial weight is logarithmically decreasing.

[0056] Preferably, the logarithmically decreasing inertia weight It is obtained through the following formula:

[0057]

[0058] in, λ is the inertia weight adjustment factor, which is a constant in the range (0,1); T max Let be the maximum number of iterations for the bat's flight, and 'a' be a constant.

[0059] Preferably, the linked update includes defining {x} μi t ,x ωj t} represents a set of bat positions that reach the globally optimal objective function value at time t, beyond the time limit.

[0060] Where i,j=argmin {i,j} F(x μi t ,x ωj t

[0061] Within the constraints, the velocity and position of the black bat at time t are updated as follows:

[0062]

[0063] The gray bat's velocity and position at time t are updated as follows:

[0064]

[0065] Among them, is the logarithmically decreasing inertia weight, v represents the velocity, and x represents the position.

[0066] Preferably, during the local search: If the bat flies to a new position better than {x μ t-1 ,x ω t-1}, the bat will perform a local search around this position. During the local search, the random walk method is adopted. That is, when the respective objective functions satisfy H1(x μ t ) < H1(x μ t-1 ) or H2(x ω t ) < H2(x ω t-1 ), and when the random condition and the constraint condition are satisfied, respectively:

[0067]

[0068] Among them, H1 represents the objective function 1, H2 represents the objective function 2, the random variable ε follows a uniform distribution on [-1, 1], represents the average sound intensity of the t-th generation in the black bat / grey bat population. At each moment, the pulse sound intensity and the pulse emission frequency are updated according to the formula:

[0069]

[0070] is the pulse sound intensity emitted by the μ / ω-th bat at the t-th generation, α is the pulse sound intensity attenuation factor, represents the pulse emission frequency of the μ / ω-th bat at the t-th generation, and γ represents the adjustment factor of the pulse emission frequency; at the end of each moment, it is judged whether the maximum number of iterations is reached. If so, the search is stopped and the position and fitness value of the bat corresponding to the global optimal solution are output. Otherwise, the search continues.

[0071] The technical solution adopted by this application can achieve the following beneficial effects:

[0072] This invention provides a semi-distributed scheduling method for cross-domain traffic in TSN based on a two-color cooperative bat algorithm. In each local TSN network within the global TSN network, an intra-domain scheduler is deployed. Each intra-domain scheduler collects and reports the traffic transmission requirements within its corresponding local TSN network. A cross-domain coordinator in the global TSN network communicates with each intra-domain scheduler to aggregate the reported traffic transmission requirements from each intra-domain scheduler, obtaining a traffic set. This traffic set is then distributed to each intra-domain scheduler. Upon receiving the calculated promised delay, the cross-domain coordinator generates an inter-domain scheduling policy using an inter-domain routing method and distributes the inter-domain scheduling policy to each intra-domain scheduler. The system performs distributed scheduling of allocated traffic among nodes and links within the domain based on the received inter-domain scheduling policy. Intra-domain traffic scheduling aims to optimize intra-domain scheduling, minimizing the sum of the total latency times of all flows reaching the destination node. Inter-domain routing aims to optimize load balancing, solving the problem of generating gating list configuration information for multi-domain fusion, improving the globality of intra-domain network scheduling, breaking through information barriers between multiple domains, and supporting flexible domain-level routing. Joint optimization of intra-domain traffic scheduling and inter-domain routing is performed using a two-color cooperative bat algorithm. By jointly optimizing a large-scale search problem in a high-dimensional discrete space, a globally optimal solution is obtained. This globally optimal solution is used to reallocate and select intra-domain traffic scheduling and inter-domain routing, strengthening the globality of intra-domain network scheduling and improving the scheduling efficiency of global TSN traffic. Attached Figure Description

[0073] Figure 1 This is the semi-distributed scheduling architecture for TSN cross-domain traffic in this invention.

[0074] Figure 2 This is an interactive flowchart of the cross-domain semi-distributed scheduling of TSN traffic in this invention.

[0075] Figure 3 This is a schematic diagram of the TSN stream cross-domain semi-distributed scheduling method based on dual-color cooperative bats in this invention. Detailed Implementation

[0076] To facilitate understanding of this application, a more comprehensive description will be provided below with reference to the accompanying drawings. Preferred embodiments of this application are also given. However, this application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to enable a more thorough and complete understanding of the disclosure of this application.

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0078] This embodiment provides a semi-distributed scheduling method for cross-domain traffic of TSN based on the two-color cooperative bat algorithm, including the following steps:

[0079] S10. Deploy an intra-domain scheduler in each local TSN network within the global TSN network scope. Each intra-domain scheduler is responsible for traffic scheduling within its corresponding local TSN network. Each intra-domain scheduler collects traffic transmission requirements within its corresponding local TSN network and reports the traffic transmission requirements within the local TSN network.

[0080] S20. Set up a cross-domain coordinator in the global TSN network. The cross-domain coordinator is communicatively connected to each of the intra-domain schedulers. The cross-domain coordinator is responsible for the path selection of each of the local TSN networks. The cross-domain coordinator summarizes the traffic transmission requirements in the local TSN network reported by each intra-domain scheduler to obtain a traffic set, and sends the traffic set to each of the intra-domain schedulers.

[0081] S30. After receiving the traffic set, each intra-domain scheduler calculates the committed delay using the intra-domain traffic scheduling method and reports the calculated committed delay to the cross-domain coordinator.

[0082] S40. After receiving the calculated promised delay, the cross-domain coordinator generates an inter-domain scheduling policy through an inter-domain routing method and distributes the inter-domain scheduling policy to each intra-domain scheduler. The intra-domain scheduler performs distributed scheduling of the allocated traffic among intra-domain nodes and links according to the received inter-domain scheduling policy.

[0083] S50. The server in the domain scheduler performs joint optimization of traffic scheduling and path selection in the local TSN network. The two-color cooperative bat algorithm is used to solve the problem and obtain the global optimal solution for traffic scheduling and path selection in the local TSN network, so as to improve the scheduling efficiency of global TSN traffic.

[0084] In this embodiment, Figure 1A semi-distributed scheduling architecture for cross-domain traffic in TSN is presented. Within the global TSN network, it is assumed that each local TSN network has an intra-domain scheduler deployed. At the same time, there is a cross-domain coordinator in the network that can communicate with each intra-domain scheduler. The intra-domain scheduler is responsible for traffic scheduling within its corresponding local TSN network, which includes: calculating the path planning of the traffic it carries and GCL (Gate Control List) gating scheduling to ensure that traffic arrives on demand and optimize the overall transmission latency; the cross-domain coordinator further considers the cross-domain link overhead.

[0085] Figure 2 The interaction flow between the intra-domain scheduler and the cross-domain coordinator in S10 to S40 of this embodiment is given. Each intra-domain scheduler collects the traffic transmission requirements within its corresponding local TSN network and reports the traffic transmission requirements within the local TSN network. The cross-domain coordinator summarizes the traffic transmission requirements reported by each intra-domain scheduler to obtain the global traffic transmission requirements, i.e., the traffic set, and distributes the traffic set to each intra-domain scheduler. After receiving the traffic set, each intra-domain scheduler performs intra-domain traffic scheduling... The promised delay is calculated using a method that includes a lower and upper bound for the delay caused by prioritizing or postponing the scheduling of each traffic flow. The calculated promised delay is then reported to the cross-domain coordinator. Upon receiving the calculated promised delay, the cross-domain coordinator generates an inter-domain scheduling policy using an inter-domain routing method and distributes the inter-domain scheduling policy to each intra-domain scheduler. The intra-domain scheduler then performs distributed scheduling of the allocated traffic among intra-domain nodes and links according to the received inter-domain scheduling policy.

[0086] Since the promised delay upper and lower bounds obtained by the intra-domain traffic scheduling method affect inter-domain routing, and inter-domain routing also affects intra-domain traffic scheduling, in a semi-distributed architecture, when the two are solved as independent problems, the optimality of global traffic scheduling will be difficult to guarantee. In order to improve the scheduling efficiency of global TSN traffic as much as possible, this embodiment uses the two-color cooperative bat algorithm to jointly optimize the traffic scheduling method and the inter-domain routing method.

[0087] Specifically, the intra-domain traffic scheduling method includes the following steps:

[0088] S31. Intra-domain traffic scheduling must ensure that the end-to-end transmission time of each TSN flow does not exceed its deadline. Simultaneously, the total traffic scheduling time for the entire TSN network should be minimized to make the overall GCL (Gate Control List) scheduling table as compact as possible. The intra-domain TSN network topology with TSN switches as nodes is abstracted into a directed graph G = (V, E), where V represents the set of nodes and E represents the set of links. V contains two types of nodes: internal nodes and cross-domain nodes, denoted by vi. in and v e This indicates that node v i to v j The link between them is represented as e ij The set of all flows within this domain is F, where each flow f i Represented as a quintuple f i =(T i D i ,L i ,st i ,des i ), where T i D is the period of the flow. i The data frames that make up this stream, L i st is the deadline for this stream. i ,des i These are the source and destination nodes of the stream, respectively. To ensure timely and accurate delivery of the data stream during transmission within the TSN domain, the following constraints must be met:

[0089] S32. Stream transmission order constraint: For the same link, the transmission time of the first frame should be non-negative, and the frames should be transmitted in chronological order.

[0090]

[0091] S33. Frame Collision Constraint: Within the same transmission time slot, link resources should be exclusively occupied by the current flow; otherwise, collisions will occur between different flows. Where T... i and T j f i and f j The corresponding flow period, where m and n are non-negative integers:

[0092]

[0093] S34. Intra-domain path constraints: TSN flows are transmitted in the topology according to the order of the links. For any adjacent link e ab ,e bc ∈E, we have:

[0094]

[0095] S35. Traffic cutoff time constraint: The end-to-end delay of traffic should not exceed its cutoff time.

[0096]

[0097] S36. Objective 1: The objective function for intra-domain traffic scheduling is defined as the sum of the times required for each flow to reach its destination node.

[0098]

[0099] Intra-domain traffic scheduling will result in a GCL scheme for each intra-domain traffic, as well as the corresponding latency for each traffic when the scheme is adopted;

[0100] In S32 to S36 above, with Indicates flow f i In the k-th frame on link e, This indicates the opening time of GCL. This indicates the GCL's closing time. Within the domain, the link propagation delay can be considered zero, and because time-slot conflict-free scheduling is used, the queuing delay is also zero. Therefore, the one-hop delay equals the switch's internal processing delay plus the outgoing port transmission delay.

[0101] Specifically, the inter-domain routing selection method includes the following steps:

[0102] S41. The goal of inter-domain traffic routing is to make reasonable routing decisions for each flow at the entire network level based on the flow transmission demand information reported by the intra-domain scheduler and the latency commitment for each flow. Let the network topology covering multiple TSN domains be G' =<D,E> Where D represents the set of TSN domains in the network, and E represents the set of cross-domain links connecting the various domains. The aggregate of traffic reported by all TSN domains is F', where each flow f i Represented as a quintuple f i =(P i U i ,L i ,st i ,des i ), where P i U is the lower bound of the latency commitment for this traffic in each domain. i L is the upper bound of the latency commitment for this stream by each domain. i st is the deadline for this stream. i ,des iThese are the source and destination nodes of the flow, respectively. Assuming the cross-domain scheduler is unaware of the resource details of each domain and makes decisions based only on partial information, details such as flow period and data frame composition are no longer relevant at this stage. The goal of this stage is for the algorithm to process the input directed graph G' =<D,E> Given the traffic set F', calculate the optimal transmission path set R for each traffic item across domains to obtain the optimal traffic success rate and average latency. Between domains, link propagation latency cannot be considered zero; assume the inter-domain link latency is... Where, d a and d b For adjacent domains, the flow f i The lower bound of the delay commitment in the d-domain is: The upper bound of the delay commitment is Lower bound of delay commitment Defined as d-domain priority scheduling f i At that time, it is assumed that the flow set F within the domain contains only a single flow f. i At that time, the latency value output by the intra-domain traffic scheduling method; the upper bound of the latency commitment is... Defined as follows: Domain d prioritizes scheduling all other traffic within the traffic set F within the domain, and then schedules a single traffic f last. i The latency value output by the intra-domain traffic scheduling method.

[0103] S42. Inter-domain path constraints: TSN flow f i Path R i It should be st i Starting from the point des i As the endpoint, it is connected at the network level and has no loops:

[0104]

[0105] S43. Flow cutoff time constraint: TSN flow f i The end-to-end delay consists of intra-domain transmission delay and inter-domain link delay. The delay should not exceed its specified deadline. Within this stage constraint, intra-domain transmission delay only considers the optimal case, i.e., the case where the lower bound of the delay commitment is achieved:

[0106]

[0107] S44. Objective 2: This embodiment sets the objective function for inter-domain traffic routing selection from a load balancing perspective:

[0108]

[0109] Inter-domain routing will result in a domain-level routing scheme for global traffic throughout the entire TSN network.

[0110] The promised latency upper and lower bounds obtained through intra-domain traffic scheduling methods affect inter-domain routing. Conversely, inter-domain routing also affects intra-domain traffic scheduling. In a semi-distributed architecture, when these two are solved as independent problems, the optimality of global traffic scheduling becomes difficult to guarantee. To improve the scheduling efficiency of global TSN traffic as much as possible, please refer to... Figure 3 The present invention provides the following embodiments that employ a two-color collaborative bat algorithm to jointly optimize objective 1 and objective 2:

[0111] In this embodiment, there are M bats in total, divided into black and gray categories. In each supercycle t (equal to the least common multiple of all traffic cycles), the black bats are responsible for intra-domain traffic scheduling, with a total of U bats; the gray bats are responsible for inter-domain routing selection, with a total of W bats.

[0112] The positions of the black / gray bats represent feasible solutions to the corresponding problem. During initialization, the positions of the bats are discretized in a given space to form a set of solutions. The bats are randomly distributed in the space, as shown below:

[0113]

[0114] Where vector This represents the initial position of the μ / ωth bat.

[0115] Considering the characteristics of heuristic algorithms, this embodiment adopts a real-number encoding strategy, using vector information to represent each individual bat. The specific dimension of the solution depends on the problem itself. Before the bat algorithm solves the TSN traffic scheduling problem, a suitable encoding mechanism must be established to transform the location information of individual bats into a traffic scheduling sequence with a defined topology, as shown below:

[0116] First, the vector Ordinalization based on element size yields

[0117]

[0118] Possible values ​​come from {1,2,…,N}, and they do not overlap.

[0119] Will This specifies the priority order in which the intra-domain scheduler or inter-domain coordinator selects the next-hop node for the next flow to be scheduled. For topology node n... i The ordered set of nodes directly connected to it is cw i =[…,n α0 ,…,n β0 ,…,n γ0 [,...]. Given a TSN stream f jThe connection node will be determined based on f. j Destination address des j The minimum distances, sorted from smallest to largest, are d. i,j =[…,n α ,…,n β ,…,n γ [,...]. Combining two ordered sets, select the item with the smallest sum of ordinal numbers in both sets as the given TSN stream f. j The next hop node (excluding the previous hop node).

[0120] After randomly initializing the bats' positions, the bats begin echolocation foraging. In each supercycle t, the foraging process of each bat, i.e., the velocity and position update, is divided into three stages: independent update, linked update, and local search.

[0121] Independent Updates: For black / gray bats, the proposed algorithm provides the following independent updates regarding velocity and position:

[0122] f μ / ω =f μ / ωmin +(f μ / ωmax -f μ / ωmin )rand

[0123]

[0124] In the above formula, Let μ be the flight speed of the μ / ωth black / gray bat at time t and time t-1, and let its dimension be... The dimensions are the same, rand is a random factor generated by the Chebyshev mapping (rand∈0,1), and it is continuously updated as it is used, therefore the pulse frequency f μ / ω It has randomness and satisfies f μ / ωmin ≤f μ / ω ≤f μ / ωmax , Let t be the position of the black / gray bat after independent updates, ∈ be the mutation weight, and C(0,1) be a random number generated by the Cauchy probability distribution with a proportional parameter t=1. This allows the algorithm to undergo a large degree of mutation in the early stage and a small degree of mutation in the later stage, so that the algorithm is based on convergence ability and can avoid getting trapped in local optima. The logarithmically decreasing inertia weight is expressed as:

[0125]

[0126] in λ is the inertia weight adjustment factor, which is a constant in the range (0,1); T max This represents the maximum number of iterations for the bat's flight; 'a' is a constant used to adjust the update speed, and can generally be set to 1. As the number of iterations increases, it decreases rapidly in the early stage and slowly in the later stage, achieving a rapid reach to the relatively optimal range and then conducting a fine search to improve the accuracy.

[0127] Linkage update: Considering the problem that inter-domain traffic scheduling and cross-domain routing selection are not completely independent, at the end of each super-cycle t, the positions and speeds of black bats and gray bats will be updated in linkage according to the objective function:

[0128] Define {x μi t ,x ωj t} to represent a set of bat positions that achieve the global optimal objective function value at time t of the super-cycle. Among them, i, j = argmin {i,j} F(x μi t ,x ωj t ). F(x μi t ,x ωj t ) is obtained by aggregating the respective in-domain schedulers to the cross-domain coordinator.

[0129] Within the constraint conditions, the speed and position of the black bat at time t are updated as:

[0130]

[0131] The speed and position of the gray bat at time t are updated as:

[0132]

[0133] Local search: Considering its own objective function, if a bat flies to a new position better than {x μ t-1 ,x ω t-1}, the bat will conduct a local search around this position. When conducting local search, a random walk method is adopted. That is, when the respective objective functions satisfy H1(x μ t ) < H1(x μ t-1 ) or H2(x ω t ) < H2(x ω t-1 ), and the random condition and constraint conditions are satisfied, respectively:

[0134]

[0135] Among them, the random variable ε follows a uniform distribution on [-1, 1], The average sound intensity of generation t in the black / gray bat colony is represented by the pulse sound intensity and pulse emission frequency, which are updated at each time step (each generation) according to the following formula:

[0136]

[0137] Let be the pulse intensity emitted by the μ / ω-th bat in the t-th generation, and α be the pulse intensity attenuation factor, satisfying... Let γ represent the pulse transmission frequency of the μ / ω-th bat in the t-th generation, and let γ represent the adjustment factor of the pulse transmission frequency, satisfying 0≤γ≤1.

[0138] At the end of each time step, it is determined whether the termination condition has been met. The termination condition is whether the maximum number of iterations has been reached. If so, the search is stopped and the position and fitness value of the bat corresponding to the global optimal solution are output. Otherwise, the search continues.

[0139] For example: When operating, first input: global TSN network G', each TSN network domain {G 1 G 2 ,…}, global traffic set F', traffic sets within each domain {F 1 ,F 2 ...}, the population size of the two-colored bats U, W, the initial value of the chaotic sequence ψ0, and the maximum impulse intensity Maximum pulse frequency upper limit of pulse frequency f μ / ωmax Lower limit f μ / ωmin Sound intensity attenuation coefficient α, frequency adjustment coefficient γ, and maximum number of iterations T max Inertia weight adjustment factor λ, variation weight ∈;

[0140] Final output: Optimal intra-domain traffic scheduling and inter-domain routing results. The specific steps are as follows:

[0141] Step 1: Initialization: Generate initial positions for μ = 1, 2, ..., U and ω = 1, 2, ..., W respectively. Calculate the global objective function value at t=0 based on the bat's initial position. Obtain the optimal solution at the current moment

[0142] Step 2: During the independent update phase, adjust the frequency of the Black Bat μ and update its speed and position;

[0143] Step 3: Independent update phase, adjust the frequency of Gray Bat ω, and update its speed and position;

[0144] Step 4: During the linkage update phase, based on the optimal... Update the speeds and positions of all bats;

[0145] Step Five: In the local search phase, generate a new solution through random walk

[0146] Step Six: Execute Step Two and Step Four;

[0147] Step Seven: In the local search phase, generate a new solution through random walk

[0148] Step Eight: Execute Step Three and Step Four;

[0149] Step Nine: Update

[0150] Step Ten: If, H1(x μ t ) < H1(x μ t-1 ) && meet the constraint conditions, set the optimal solution as

[0151] Step Eleven: If, H2(x ω t ) < H2(x ω t-1 ) && meet the constraint conditions, set the optimal solution as

[0152] Step Twelve: If the constraint conditions are not met, execute Step Two.

[0153] The global optimal solution can be used: and Reallocate and select the in-domain traffic scheduling and the inter-domain routing, which strengthens the globality of the in-domain network scheduling and improves the scheduling efficiency of the global TSN traffic.

[0154] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A semi-distributed scheduling method for cross-domain traffic of TSN based on the two-color cooperative bat algorithm, characterized in that, Includes the following steps: S10. Deploy an intra-domain scheduler in each local TSN within the global TSN scope. Each intra-domain scheduler is responsible for traffic scheduling within its corresponding local TSN. Each intra-domain scheduler collects the traffic transmission requirements within its corresponding local TSN and reports the traffic transmission requirements within the local TSN. S20. A cross-domain coordinator is configured in the global TSN. The cross-domain coordinator is communicatively connected to each of the intra-domain schedulers. The cross-domain coordinator is responsible for path selection for each local TSN. The cross-domain coordinator aggregates the traffic transmission requirements within the local TSN reported by each intra-domain scheduler to obtain a traffic set. and the traffic set Distribute to each of the aforementioned domain schedulers; S30. Each of the intra-domain schedulers receives the traffic set. Then, the promised delay is calculated using the intra-domain traffic scheduling method, and the calculated promised delay is reported to the cross-domain coordinator; S40. After receiving the calculated promised delay, the cross-domain coordinator generates an inter-domain scheduling policy through an inter-domain routing method and distributes the inter-domain scheduling policy to each intra-domain scheduler. The intra-domain scheduler performs distributed scheduling of the allocated traffic among intra-domain nodes and links according to the received inter-domain scheduling policy. S41. Let the network topology covering multiple local TSNs be as follows: , This represents the set of local TSNs in the network. This represents the set of links, which is the set of traffic reported by all local TSNs. Calculate the set of optimal transmission paths for each traffic flow between domains. The traffic set Each flow in Represented as: ； in, To provide a lower bound for the latency commitment of this traffic in each domain, To define the upper bound of the latency commitment for this traffic for each domain, For the deadline of this traffic, These are the source and destination nodes of the traffic, respectively. S42. Inter-domain path constraints include the traffic set. Within each flow Optimal transmission path Should be Starting from, with End point: ； ； in, For each traffic flow, the set of optimal transmission paths between domains For each traffic item, the optimal transmission path between domains, For the source node of this traffic, For the destination node of this traffic, and For any two adjacent fields; S43. When there is a flow deadline constraint, the flow... The end-to-end delay consists of intra-domain transmission delay and inter-domain link delay, and the delay does not exceed its specified deadline: ； in, For traffic exist The lower bound of the latency commitment within the domain, This is the deadline for the traffic. For links; S44. The objective function for selecting inter-domain routing traffic in the inter-domain routing selection method is: ； in Represents objective function 2, For traffic exist The lower bound of the latency commitment within the domain, For traffic exist Upper bound of latency commitment within the domain; The two-color cooperative bat algorithm includes the following steps: S50. The server in the domain scheduler performs joint optimization of traffic scheduling and path selection within the local TSN, and uses the two-color cooperative bat algorithm to solve the problem, thereby obtaining the global optimal solution for traffic scheduling and path selection within the local TSN, so as to improve the scheduling efficiency of global TSN traffic. S51. Will Bats are divided into Only black bats and There are only gray bats; the black bats are responsible for intra-domain traffic scheduling, and the gray bats are responsible for inter-domain routing selection. S52. Initial bat positions: Discretize the bat positions in a given space to form a set of solutions. The bats are randomly distributed in the space, and the initial positions of the bats are: ； Where, vector Representing the The initial position of the bat; S53. A real-number encoding strategy is adopted, using vector information to represent each individual bat, and the vector... Ordinalize by the size of the element to obtain The priority order for obtaining individual bat location information is as follows: ； S54. In each supercycle Within the system, each bat engages in foraging, updating its speed and position. By iteratively updating the bats' speed and position, the system seeks the globally optimal solution. The speed and position updates are divided into three stages: independent updates, linked updates, and local search.

2. The semi-distributed scheduling method for TSN cross-domain traffic based on the dual-color cooperative bat algorithm according to claim 1, characterized in that, The intra-domain traffic scheduling method includes the following steps: S31. Define the network topology of the local TSN as a directed graph. , Represents a set of nodes. The set of links, the set of nodes Including internal nodes and cross-domain nodes The traffic set is The traffic set Each flow in Represented as: ； in For the period of this traffic, This consists of data frames for this traffic. This is the deadline for the traffic. These are the source and destination nodes of the traffic, respectively. S32. When constraining the transmission order of traffic, for the same link, the transmission time of the first frame should be non-negative, and the frames should be transmitted in chronological order: ； ； in, Represents each flow in the flow set F The kth frame on link e This indicates GCL's closing time. This indicates the opening time of GCL. , , All are indexes; S33. Under frame collision constraints, link resources should be exclusively occupied by the current traffic within the same transmission time slot: ； ； in, and for and The corresponding traffic period, where j is the index. , It is a non-negative integer; S34. Intra-domain path constraints include the order in which local TSN traffic is transmitted within the topology, conforming to the link sequence: ； in, , For link set In any adjacent link, both ab and bc are indices; S35. Deadline constraints for each flow include ensuring that the end-to-end delay of the flow does not exceed its deadline: ； in, This is the deadline for the traffic. The destination node for this traffic; S36. Define the objective function for intra-domain traffic scheduling, which is to minimize the sum of the times required for each traffic flow to reach its destination node, including: ； in, , This represents objective function 1.

3. The semi-distributed scheduling method for TSN cross-domain traffic based on the dual-color cooperative bat algorithm according to claim 2, characterized in that, The algorithm for the independent update is as follows: ； ； ； in, For the first / The flight speed of only black / gray bats at time t, For the first / The flight speed of only black / gray bats at time t-1 For the random factors generated by the Chebyshev mapping, , For black / gray bat pulse frequency, This represents the lower limit of the black / gray bat pulse frequency. This represents the upper limit of the black / gray bat pulse frequency. The position of the black / gray bat at time t-1. The position of the black / gray bat after independent updates at time t. For variation weights, For proportional parameters Random numbers generated by the Cauchy probability distribution The inertial weight is logarithmically decreasing.

4. The semi-distributed scheduling method for TSN cross-domain traffic based on the dual-color cooperative bat algorithm according to claim 3, characterized in that, The logarithmically decreasing inertial weight It is obtained through the following formula: ； in, , , These are inertia weight adjustment factors, all of which are constants within the range of (0,1); The maximum number of iterations for bat flight, For constants .

5. The semi-distributed scheduling method for TSN cross-domain traffic based on the dual-color cooperative bat algorithm according to claim 4, characterized in that, The linked update includes the definition. This represents a set of bat positions that reach the globally optimal objective function value at time t, beyond the period. in, ; Within the constraints, the velocity and position of the black bat at time t are updated as follows: ； ； The gray bat's velocity and position at time t are updated as follows: ； ； in, v represents velocity, and x represents position.

6. The semi-distributed scheduling method for TSN cross-domain traffic based on the dual-color cooperative bat algorithm according to claim 5, characterized in that, During the local search: if the bat flies to a location larger than... To find a better new location, the bats will conduct a local search around that location, using a random walk method during the local search, i.e., searching for locations where their respective objective functions satisfy... or When, and satisfying both the random condition and the constraint condition, we have: ； ； in, Represents objective function 1, Represents objective function 2, random variable Following a uniform distribution on [−1,1], the pulse intensity and pulse emission frequency are updated at each time step according to the formula: ； ； For the first / The pulse intensity emitted by a single bat in generation n, where is the pulse intensity attenuation factor. Representing the / The pulse emission frequency of only one bat in the 𝑡 generation, The adjustment factor represents the pulse emission frequency; at the end of each time step, it is determined whether the maximum number of iterations has been reached. If so, the search is stopped and the position and fitness value of the bat corresponding to the global optimal solution are output; otherwise, the search continues.

Images