Resource allocation method and system for immediate or advance reservation requests

Abstract

This invention belongs to the field of network resource allocation technology, specifically relating to a method and system for allocating resources for immediate or advance reservation requests. The method includes the following steps: constructing and initializing a cloud-edge collaborative elastic optical network, generating a set of connection requests; establishing candidate paths for the connection requests; constructing a two-dimensional resource state model based on the required number of spectrum slots for the candidate paths; evaluating the link resource state of the candidate paths; obtaining the priority of the candidate paths; classifying the connection requests into immediate reservation connection requests and advance reservation connection requests; selecting candidate paths and allocating spectrum resources for different types of connection requests according to the priority order; and releasing and updating the spectrum resources of the candidate paths and the computing resources of the nodes after the connection request service is completed. This invention achieves optimized allocation of spectrum resources in the network, effectively solving the problems of high blocking rates and low spectrum utilization caused by a large number of connection requests in a short period of time.

Description

Technical Field

[0001] The present invention relates to the technical field of network resource allocation, and in particular to a resource allocation method and system for instant or advance reservation requests. Background Art

[0002] With the rise of data center applications such as data migration and cloud computing, the original flexible optical network spectrum resource model is no longer suitable for current needs. Today, with the rapid development of the network, the bandwidth demand continues to rise, and the number of connection requests is growing exponentially. In the network, especially when there are a large number of immediate reservation requests and advance reservation requests, it is particularly important to reasonably allocate network resources through more reasonable routing selection and spectrum allocation methods.

[0003] Today, as mobile data accounts for a considerable share of the total Internet traffic, emerging applications such as cloud computing, video on demand, and big data migration have triggered a sharp increase in the amount of information, accompanied by a large amount of content and extremely high network traffic. How to effectively classify and process these connection requests to improve the efficiency of network systems has always been the focus of optical network research. By making full use of the advantages of today's edge cloud computing networks, more intelligent and reasonable network resource scheduling can be implemented. In advance reservation requests, the size of the maximum tolerated delay time reflects the urgent need for spectrum resource allocation. Therefore, for advance reservation requests, by giving full play to the high computing and storage capabilities of edge cloud computing networks, and considering the two dimensions of time domain and spectrum domain, the optimal allocation of spectrum resources in the network can be achieved, thereby significantly improving the high blocking rate and low spectrum utilization caused by a large number of connection requests in a short period of time.

[0004] For dynamic traffic, most current network system models only consider immediate reservation requests, which are issued when network services or spectrum resources are actually needed. However, if the spectrum or computing resources are not available when they are actually needed, the request will be blocked. For some users of real-time applications (such as online meetings and live broadcasts) that need to ensure that network services are available at a specified time and for a specified duration, any network service failure may be intolerable. In order to meet the needs of these applications, it is necessary for the network system to meet both immediate reservation request and advance reservation request services. This not only helps to provide reliable services to network users, but also helps to plan the allocation of spectrum and computing resources of the network more efficiently. Although advance reservation technology has been widely studied in the field of non-optical networks, it is relatively less studied in the field of cloud-edge elastic optical networks. Summary of the invention

[0005] To this end, the technical problem to be solved by the present invention is to overcome the high blocking rate and low spectrum utilization problems caused by a large number of connection requests in a short period of time in the prior art, give full play to the high computing and storage capabilities of the edge cloud computing network, and consider the two dimensions of time domain and spectrum domain to achieve optimal allocation of spectrum resources in the network.

[0006] To solve the above technical problems, the present invention provides a resource allocation method for immediate or advance reservation requests, the method comprising the following steps:

[0007] S1: Build and initialize the cloud-edge collaborative elastic optical network and generate a set of connection requests;

[0008] S2: Establish a candidate path for the connection request, construct a two-dimensional resource status model, and then establish a two-dimensional resource status matrix of the candidate path based on the spectrum resource status of all links on the candidate path. Calculate the link resource state value LS of the candidate path P , thus obtaining the LS of all candidate paths P , sort them and get the priority among all candidate paths;

[0009] Among them, α and β represent the influence weights of the time domain and spectrum domain in route selection, respectively, and γ is a preset parameter. α>0, β>0, γ>0, T P is the time domain continuity value of the current candidate path state, F P Indicates the continuity value of the spectrum domain in the current candidate path, OC P Indicates the overall resource occupancy value of the current candidate path. F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t; hop(p s,d ) represents the number of nodes that the candidate path p from the source node s to the destination node d passes through;

[0010] S3: Classify the connection requests into immediate reservation connection requests and advance reservation connection requests, select candidate paths to allocate spectrum resources for different types of connection requests according to the order of priority, and release and update the spectrum resources of the candidate paths and the computing resources of the nodes after the connection request service is completed.

[0011] In one embodiment of the present invention, the cloud-edge collaborative elastic optical network G(N,E,D st ,S,T), where N represents the set of nodes in the network, E represents a set of fiber links, S = {s1,s2,...,s s} represents the set of spectrum slots available in each fiber link, D st The set consists of a set of physical distances between each pair of adjacent nodes in the set N, T = {t1, t2, ..., t T} represents the set of time slots in the network that can be provided to serve or reserve immediate or advance reservation requests, |S| and |T| represent the number of spectrum slots and time slots, respectively.

[0012] In one embodiment of the present invention, the connection request CR (s, d, C, t a ,td max ,H t ), s represents the source node of the connection request, d represents the destination node of the connection request, C represents the capacity of the connection request, t a is the arrival time of the connection request, td max is the maximum tolerable delay time of the connection request, H t is the requested hold time.

[0013] In one embodiment of the present invention, the two-dimensional resource status matrix is:

[0014]

[0015] Where F is the maximum number of spectrum slots, T is the maximum number of predictable time slots, represents the occupied state of frequency slot f at time t, when , it indicates that the frequency slot is occupied or reserved at that moment; if It means that the frequency slot is not occupied at this moment; l represents the candidate path.

[0016] In one embodiment of the present invention, the time domain continuity value T of the current candidate path state is P The calculation method is:

[0017]

[0018] Among them, F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t, Representation Matrix The inverted matrix, represents the two-dimensional resource state matrix of frequency slot f at time t+1, Representation Matrix The inverted matrix.

[0019] In one embodiment of the present invention, the continuity value F of the spectrum domain in the current candidate path PThe calculation method is:

[0020]

[0021] Among them, F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t, Representation Matrix The inverted matrix.

[0022] In one embodiment of the present invention, the instant reservation connection request is a connection request with a maximum tolerable delay time of 0 and is processed as soon as the request arrives, and the advance reservation connection request is a connection request with a maximum tolerable delay time of not 0 and does not need to be processed immediately when the request arrives.

[0023] In one embodiment of the present invention, in S3, the method for selecting candidate paths for different types of connection requests to allocate spectrum resources includes:

[0024] S31: selecting an optimal candidate path according to the priority, and determining whether the required number of spectrum slots is available on the optimal candidate path. If yes, allocating spectrum resources for the connection request according to the selected candidate path, and the connection request is successfully established; if no, executing S32;

[0025] S32: Determine the type of the connection request. If the connection request is an immediate reservation connection request, the connection request fails. If the connection request is an advance reservation connection request, execute S33.

[0026] S33: Determine within the maximum tolerable delay time after the advance reservation connection request arrives, select the optimal candidate path according to the priority, and determine whether the required number of spectrum slots are available on the optimal candidate path; if so, allocate spectrum resources for the connection request according to the selected candidate path, and the connection request is successfully established; if not, the connection request fails.

[0027] Based on the same inventive concept, the present invention also provides a resource allocation system for immediate or advance reservation requests, including the following modules:

[0028] The network construction and initialization module is used to build and initialize the cloud-edge collaborative elastic optical network;

[0029] A connection request generation module, configured to generate a set of connection requests based on the cloud-edge collaborative elastic optical network;

[0030] The candidate path generation and priority calculation module is used to establish the candidate path of the connection request, construct a two-dimensional resource status model, and then establish a two-dimensional resource status matrix of the candidate path based on the spectrum resource status of all links on the candidate path. Calculate the link resource state value LS of the candidate path P , thus obtaining the LS of all candidate paths P , sort them and get the priority among all candidate paths;

[0031] Among them, α and β represent the influence weights of the time domain and spectrum domain in route selection, respectively, and γ is a preset parameter. α>0, β>0, γ>0, T P is the time domain continuity value of the current candidate path state, F P Indicates the continuity value of the spectrum domain in the current candidate path, OC P Indicates the overall resource occupancy value of the current candidate path. F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t; hop(p s,d ) represents the number of nodes that the candidate path p from the source node s to the destination node d passes through;

[0032] A spectrum resource allocation module, configured to select candidate paths to allocate spectrum resources to different types of connection requests according to the order of the priorities and the classification types of the connection requests;

[0033] The resource release module is used to release and update the spectrum resources of the candidate path and the computing resources of the node after the connection request service is completed.

[0034] The above technical solution of the present invention has the following advantages compared with the prior art:

[0035] 1. The present invention integrates edge computing and cloud computing elastic optical networks to effectively handle a large number of simultaneous instant appointment and advance booking requests to meet the growing network demand.

[0036] 2. Aiming at the routing and spectrum allocation issues of instant and advance reservations in elastic optical networks, the purpose of processing instant and advance reservation service requests in elastic optical networks is achieved, reducing network congestion rate, improving spectrum utilization, and realizing improved network performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below according to specific embodiments of the present invention in conjunction with the accompanying drawings, wherein

[0038] Figure 1 is a flow chart of the method of the present invention;

[0039] Figure 2 is a specific flow chart of the method in an embodiment of the present invention;

[0040] Figure 3 It is a NSFNET topology diagram in an embodiment of the present invention;

[0041] Figure 4 is a diagram of a cloud-edge collaborative elastic optical network framework in an embodiment of the present invention;

[0042] Figure 5 is a spectrum utilization status result of a candidate path based on a two-dimensional resource model in an embodiment of the present invention;

[0043] Figure 6 It is a spectrum utilization status result of optimizing the candidate paths based on the link resource utilization status in the embodiment of the present invention. DETAILED DESCRIPTION

[0044] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0045] Embodiment 1

[0046] When the elastic optical network needs to handle a large number of different types of reservation request services, such as Figures 1-2 As shown, the present invention proposes a resource allocation method for immediate or advance reservation requests. In order to effectively improve the utilization rate of network resources and reduce the network congestion rate, the above method includes the following key steps:

[0047] Step S1: construct and initialize the cloud-edge collaborative elastic optical network and generate a set of connection requests;

[0048] Step S2: Use K shortest path algorithm to establish candidate paths for the connection request, construct a two-dimensional resource status model, and then establish a two-dimensional resource status matrix of the candidate path based on the spectrum resource status of all links on the candidate path. Calculate the link resource state value LS of the candidate path P , thus obtaining the LS of all candidate paths P , sort them and get the priority among all candidate paths;

[0049] Among them, α and β represent the influence weights of the time domain and spectrum domain in route selection, respectively, and γ is a preset parameter. α>0, β>0, γ>0, T P is the time domain continuity value of the current candidate path state, F PIndicates the continuity value of the spectrum domain in the current candidate path, OC P Indicates the overall resource occupancy value of the current candidate path. F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t; hop(p s,d ) represents the number of nodes that the candidate path p from the source node s to the destination node d passes through;

[0050] Step S3: Classify the connection requests into immediate reservation connection requests and advance reservation connection requests, select candidate paths to allocate spectrum resources for different types of connection requests according to the order of priority, and release and update the spectrum resources of the candidate paths and the computing resources of the nodes after the connection request service is completed.

[0051] The cloud-edge collaborative elastic optical network G(N,E,D st ,S,T), where N represents the set of nodes in the network, E represents a set of fiber links, S = {s1,s2,...,s s} represents the set of spectrum slots available in each fiber link, D st The set consists of a set of physical distances between each pair of adjacent nodes in the set N, T = {t1, t2, ..., t T} represents the set of time slots in the network that can be provided to immediate or advance reservation requests or reserved, |S| and |T| represent the number of spectrum slots and time slots, respectively; for example, D st (i,j) is the actual distance between node i and node j in the network.

[0052] The connection request CR(s,d,C,t a ,td max ,H t ), where s represents the source node of the connection request, d represents the destination node of the connection request, C represents the capacity of the connection request, and t a is the arrival time of the connection request, td max is the maximum tolerable delay time of the connection request, H t is the requested hold time.

[0053] The maximum tolerable delay time of the connection request is 0, that is, the connection request is processed as soon as it arrives as an immediate reservation connection request, and the maximum tolerable delay time of the connection request is not 0, that is, the connection request does not need to be processed immediately after it arrives as an advance reservation connection request:

[0054]

[0055] Among them, t istart Indicates the time when the connection request processing starts. IR indicates an immediate reservation connection request, and AR indicates an advance reservation connection request.

[0056] Furthermore, the two-dimensional resource status matrix is:

[0057]

[0058] Where F is the maximum number of spectrum slots, T is the maximum number of predictable time slots, represents the occupied state of frequency slot f at time t. , it indicates that the frequency slot is occupied or reserved at that moment; if This means that the frequency slot is not occupied at this moment.

[0059] In step S2, the time domain continuity value T of the current candidate path state is P The calculation method is:

[0060]

[0061] Among them, F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t, Representation Matrix The inverted matrix, represents the two-dimensional resource state matrix of frequency slot f at time t+1, Representation Matrix The inverted matrix.

[0062] The continuity value F of the spectrum domain in the current candidate path P The calculation method is:

[0063]

[0064] Among them, F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t, Representation Matrix The inverted matrix.

[0065] In step S3, the method for selecting candidate paths for allocating spectrum resources for different types of connection requests includes:

[0066] S31: selecting an optimal candidate path according to the priority, and determining whether the required number of spectrum slots is available on the optimal candidate path. If yes, allocating spectrum resources for the connection request according to the selected candidate path, and the connection request is successfully established; if no, executing S32;

[0067] S32: Determine the type of the connection request. If the connection request is an immediate reservation connection request, the connection request fails. If the connection request is an advance reservation connection request, execute S33.

[0068] S33: Determine within the maximum tolerable delay time after the advance reservation connection request arrives, select the optimal candidate path according to the priority, and determine whether the required number of spectrum slots are available on the optimal candidate path; if so, allocate spectrum resources for the connection request according to the selected candidate path, and the connection request is successfully established; if not, the connection request fails.

[0069] Among them, the number of required spectrum slots N S The calculation method is:

[0070]

[0071] Where C represents the connection request capacity, F represents the modulation level determined based on the candidate path, and C slot It is the bandwidth capacity of a single spectrum slot under the corresponding modulation level, and GB is the number of spectrum slots of the protection bandwidth.

[0072] From the above technical solutions, the present invention effectively solves the problem of allocating immediate and advance reservation requests in elastic optical networks. In order to effectively reduce the probability of network congestion and improve spectrum efficiency, a dynamic allocation method for immediate and advance reservation requests in elastic optical networks is designed, a two-dimensional resource model is established, and the path link resource status is evaluated. Considering the time domain continuity and spectrum domain continuity of link resources from the two dimensions of time domain and frequency domain, a better path is finally selected for resource allocation; the K shortest path algorithm is used to calculate the candidate working path of the service request, and the priority of the path is obtained through the two-dimensional resource matrix. In the two-dimensional resource status model, resources are more transparent, and both immediate reservation and advance reservation requests can be processed simultaneously.

[0073] In order to further illustrate the beneficial effects of the present invention, in this embodiment, Figure 3 The experiment was carried out in the network topology shown in the figure. Figure 3The NSFNET network topology shown has a total of 14 nodes and 21 bidirectional links. The value on the fiber link represents the length of the link in km. The bandwidth of each spectrum slot is set to 12.5 GHz, and the capacity of the fiber link is 120 spectrum slots. The maximum number of services or reserved time slots provided by the cloud-edge elastic optical network for immediate or advance reservation requests is 20. The capacity range C of the generated requests is 12.5 to 200 Gb / s, using different modulation format levels.

[0074] Figure 4 In the paper, the elastic optical network is mainly divided into the cloud domain and the edge region. The elastic optical network architecture meets the computing and storage requirements of resource scheduling and reservation for advance reservation and immediate reservation requests. In the elastic optical network, the current and future occupancy and reservation status of candidate link resources can be perceived. In addition, the holding time of advance reservation or immediate reservation request is an integer multiple of the time slot, and the request can only be scheduled after the initial time.

[0075] exist Figure 5 In it is explained how to represent the spectrum utilization status of candidate paths based on a two-dimensional resource status matrix. Figure 5 (a) shows the path from A to C, which contains link a and link b. Figure 5 (b) and Figure 5 (c) shows the allocated advance reservation and immediate reservation requests in link a and link b, respectively. Requests CR1, CR5, and CR7 are advance reservation requests, and requests CR2, CR3, CR4, and CR6 are immediate reservation requests. Figure 5 (d) shows the complete resource usage status of the path under the matrix representation, where the shaded part represents occupation, i.e. 1, and the blank part indicates that the resource is available, that is, is 0. Therefore, according to the state of the matrix, the resource usage of the link can be analyzed to optimize the routing for the request.

[0076] Figure 6 Shown according to LS P In this embodiment, the values ​​of α and β are set to 1, which means that the weights of the time domain and the frequency domain in the network are equal. The value of γ is set to the unit value 1. Figure 6 (a) shows that when a request goes from source node 1 to destination node 4, there are three candidate paths: candidate path 1 (1->3->4), candidate path 2 (1->4) and candidate path 3 (1->2->4). Figure 6 (b) shows the resource occupancy status of candidate path 1, including link 4 and link 5. The two-dimensional resource status matrix of path 1 is:

[0077]

[0078] According to the formula The T under this candidate path can be obtained P1 =5.

[0079] According to the formula F P1 =5.

[0080] According to the formula Available OC P1 =12.

[0081] Therefore, based on Among them, α and β are both 1, which means that the influence weights of time domain and spectrum domain are the same when selecting routes. Similarly, by Figure 6 As shown in (c) to (d), the two-dimensional resource state matrix of candidate path 2 and candidate path 3 can be obtained as follows:

[0082]

[0083] From the two-dimensional resource state matrix, we can get LS P2 =0.46 and LS P3 =0.58. Because the LS of path 3 P The value is the largest, so path 3 is selected to allocate resources. Figure 6 Analyzing the occupation of each path, all three candidate paths have the same reserved or occupied resources, that is, a total of 12 slots are occupied, accounting for half of the total resources. Among them, path 2 has the least hops and only occupies link 1, that is, it occupies the least spectrum slot. Using the traditional routing selection method, path 2 will be selected for resource allocation. However, the current link status of path 2 is the worst, with a large amount of spectrum fragmentation and time fragmentation. LS P The larger the value, the better the resource regularity and path status of the link resources. In summary, choose LS P The path 3 with the largest value is selected as the optimal path.

[0084] Embodiment 2

[0085] Based on the same inventive concept as the resource allocation method described in Example 1, the present invention also provides a resource allocation system for immediate or advance reservation requests, including the following modules:

[0086] The network construction and initialization module is used to build and initialize the cloud-edge collaborative elastic optical network;

[0087] A connection request generation module, configured to generate a set of connection requests based on the cloud-edge collaborative elastic optical network;

[0088] The candidate path generation and priority calculation module is used to establish the candidate path of the connection request, establish the candidate path of the connection request, construct a two-dimensional resource status model, and then establish a two-dimensional resource status matrix of the candidate path based on the spectrum resource status of all links on the candidate path, according to the formula Calculate the link resource state value LS of the candidate path P , thus obtaining the LS of all candidate paths P , sort them and get the priority among all candidate paths;

[0089] Among them, α and β represent the influence weights of the time domain and spectrum domain in route selection, respectively, and γ is a preset parameter. α>0, β>0, γ>0, T P is the time domain continuity value of the current candidate path state, F P Indicates the continuity value of the spectrum domain in the current candidate path, OC P Indicates the overall resource occupancy value of the current candidate path. F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t; hop(p s,d ) represents the number of nodes that the candidate path p from the source node s to the destination node d passes through;

[0090] A spectrum resource allocation module, configured to select candidate paths to allocate spectrum resources to different types of connection requests according to the order of the priorities and the classification types of the connection requests;

[0091] The resource release module is used to release and update the spectrum resources of the candidate path and the computing resources of the node after the connection request service is completed.

[0092] The lower blocking probability obtained by the method of the present invention means that the scheme achieves higher resource utilization in terms of spectrum resources. The main reason is that the two-dimensional resource model is introduced to make resources more transparent. The final working path is determined based on the resource occupancy and reservation status of the candidate path and the link distance. The maximum tolerable delay time of each connection request is taken into account, and the allocation and reservation of immediate reservation and advance reservation requests are realized, thereby enhancing network performance.

[0093] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the protection scope of the invention.

Claims

1. A method for allocating resources for immediate or advance reservation requests, characterized in that: The following steps are involved: S1: Build and initialize the cloud-edge collaborative elastic optical network and generate a set of connection requests; S2: Establish a candidate path for the connection request, construct a two-dimensional resource status model, and then establish a two-dimensional resource status matrix of the candidate path based on the spectrum resource status of all links on the candidate path. Calculate the link resource state value LS of the candidate path P , thus obtaining the LS of all candidate paths P , sort them and get the priority among all candidate paths; Among them, α and β represent the influence weights of the time domain and spectrum domain in route selection, respectively, and γ is a preset parameter. α>0, β>0, γ>0, T P is the time domain continuity value of the current candidate path state, F P Indicates the continuity value of the spectrum domain in the current candidate path, OC P Indicates the overall resource occupancy value of the current candidate path. F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t; hop(p s,d ) represents the number of nodes that the candidate path p from the source node s to the destination node d passes through; S3: Classify the connection requests into immediate reservation connection requests and advance reservation connection requests, select candidate paths to allocate spectrum resources for different types of connection requests according to the order of priority, and release and update the spectrum resources of the candidate paths and the computing resources of the nodes after the connection request service is completed.

2. The resource allocation method for immediate or advance reservation requests according to claim 1, characterized in that: The cloud-edge collaborative elastic optical network G(N,E,D st ,S,T), where N represents the set of nodes in the network, E represents a set of fiber links, S = {s1,s2,...,s s } represents the set of spectrum slots available in each fiber link, D st The set consists of a set of physical distances between each pair of adjacent nodes in the set N, T = {t1, t2, ..., t T } represents the set of time slots in the network that can be provided to serve or reserve immediate or advance reservation requests, and |S| and |T| represent the number of spectrum slots and time slots, respectively.

3. The resource allocation method for immediate or advance reservation requests according to claim 1, characterized in that: The connection request CR(s,d,C,t a ,td max ,H t ), s represents the source node of the connection request, d represents the destination node of the connection request, C represents the capacity of the connection request, t a is the arrival time of the connection request, td max is the maximum tolerable delay time of the connection request, H t is the requested hold time.

4. The resource allocation method for immediate or advance reservation requests according to claim 1, characterized in that: The two-dimensional resource status matrix is: Where F is the maximum number of spectrum slots, T is the maximum number of predictable time slots, represents the occupied state of frequency slot f at time t, when , it indicates that the frequency slot is occupied or reserved at that moment; if It means that the frequency slot is not occupied at this moment; l represents the candidate path.

5. The resource allocation method for immediate or advance reservation requests according to claim 1, characterized in that: The time domain continuity value T of the current candidate path state P The calculation method is: Among them, F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t, Representation Matrix The inverted matrix, represents the two-dimensional resource state matrix of frequency slot f at time t+1, Representation Matrix The inverted matrix.

6. The resource allocation method for immediate or advance reservation requests according to claim 1, characterized in that: The continuity value F of the spectrum domain in the current candidate path P The calculation method is: Among them, F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t, Representation Matrix The inverted matrix.

7. The resource allocation method for immediate or advance reservation requests according to claim 1, characterized in that: The instant reservation connection request is a connection request with a maximum tolerable delay time of 0 and is processed as soon as the request arrives. The advance reservation connection request is a connection request with a maximum tolerable delay time of not 0 and does not need to be processed immediately when the request arrives.

8. The resource allocation method for immediate or advance reservation requests according to claim 1, characterized in that: In S3, the method for selecting candidate paths for different types of connection requests and allocating spectrum resources includes: S31: selecting an optimal candidate path according to the priority, and determining whether the required number of spectrum slots is available on the optimal candidate path. If yes, allocating spectrum resources for the connection request according to the selected candidate path, and the connection request is successfully established; if no, executing S32; S32: Determine the type of the connection request. If the connection request is an immediate reservation connection request, the connection request fails. If the connection request is an advance reservation connection request, execute S33. S33: Determine within the maximum tolerable delay time after the advance reservation connection request arrives, select the optimal candidate path according to the priority, and determine whether the required number of spectrum slots are available on the optimal candidate path; if so, allocate spectrum resources for the connection request according to the selected candidate path, and the connection request is successfully established; if not, the connection request fails.

9. A resource allocation system for immediate or advance reservation requests, characterized in that: The steps of implementing the method for allocating resources for immediate or advance reservation requests as claimed in any one of claims 1 to 8, the system comprising: The network construction and initialization module is used to build and initialize the cloud-edge collaborative elastic optical network; A connection request generation module, configured to generate a set of connection requests based on the cloud-edge collaborative elastic optical network; The candidate path generation and priority calculation module is used to establish the candidate path of the connection request, construct a two-dimensional resource status model, and then establish a two-dimensional resource status matrix of the candidate path based on the spectrum resource status of all links on the candidate path. Calculate the link resource state value LS of the candidate path P , thus obtaining the LS of all candidate paths P , sort them and get the priority among all candidate paths; Among them, α and β represent the influence weights of the time domain and spectrum domain in route selection, respectively, and γ is a preset parameter. α>0, β>0, γ>0, T P is the time domain continuity value of the current candidate path state, F P Indicates the continuity value of the spectrum domain in the current candidate path, OC P Indicates the overall resource occupancy value of the current candidate path. F max Indicates the maximum number of spectrum slots, T max Indicates the maximum number of predictable time slots, represents the two-dimensional resource state matrix of frequency slot f at time t; hop(p s,d ) represents the number of nodes that the candidate path p from the source node s to the destination node d passes through; A spectrum resource allocation module, configured to select candidate paths to allocate spectrum resources to different types of connection requests according to the order of the priorities and the classification types of the connection requests; The resource release module is used to release and update the spectrum resources of the candidate path and the computing resources of the node after the connection request service ends.

Images