CN115914890A - Elastic optical network maximum tolerant delay redistribution method and system based on edge cloud computing - Google Patents
Elastic optical network maximum tolerant delay redistribution method and system based on edge cloud computing Download PDFInfo
- Publication number
- CN115914890A CN115914890A CN202211346546.3A CN202211346546A CN115914890A CN 115914890 A CN115914890 A CN 115914890A CN 202211346546 A CN202211346546 A CN 202211346546A CN 115914890 A CN115914890 A CN 115914890A
- Authority
- CN
- China
- Prior art keywords
- connection request
- network
- spectrum
- cloud computing
- edge cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000001228 spectrum Methods 0.000 claims abstract description 140
- 230000005540 biological transmission Effects 0.000 claims abstract description 31
- 238000013468 resource allocation Methods 0.000 claims abstract description 25
- 230000000903 blocking effect Effects 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 239000013307 optical fiber Substances 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of elastic optical networks, and discloses a method and a system for redistributing maximum tolerant delay of an elastic optical network of edge cloud computing, wherein the method comprises the following steps: constructing and initializing an edge cloud computing elastic optical network model, generating connection requests and classifying the connection requests according to the degree of emergency according to the maximum tolerant delay time; establishing a candidate transmission path set of a connection request, calculating the number of required frequency spectrum slots of the connection request on each candidate path, and performing priority ordering on the candidate paths; network resources are distributed by combining edge cloud computing, the number of idle required frequency spectrum slots is searched on a candidate path according to the priority sequence and the type of a connection request, and the connection request is successfully established; the system comprises a network initialization module, a connection request generation module, a spectrum resource calculation module and a spectrum resource allocation module. The invention can effectively improve the resource utilization rate of the network and reduce the blocking rate of the network when huge connection requests arrive in the network.
Description
Technical Field
The invention relates to the technical field of elastic optical networks, in particular to a maximum tolerant delay redistribution method and system for an elastic optical network of edge cloud computing.
Background
In Elastic Optical Networks (Elastic Optical Networks), the fiber spectrum resources consist of continuous spectrum slots of fixed spectral width. However, with the emergence of data center applications such as data migration and cloud computing, the original flexible spectrum resource allocation method is obviously insufficient. With the rapid development of networks nowadays, the bandwidth demand is increasing day by day, the number of connection requests is also increasing exponentially, and when a large number of immediate reservation connection requests and advance reservation connection requests exist in a network in a short time, the reasonable allocation of spectrum resources by a network resource allocation method is also becoming more important.
Today, the full popularity of smartphones has made mobile data a significant percentage of the total internet traffic. New applications, such as cloud computing, video on demand, and online gaming, have led to an explosive growth in online information, including large amounts of content and extremely high network traffic. How to effectively classify and process the connection requests makes the flexible optical network more efficient. According to the urgency requirements of different connection requests for computing resource allocation, the connection requests can be classified into advance reservation connection requests and immediate reservation connection requests. According to the advantages of the edge cloud computing network, more reasonable network resource allocation can be realized. The magnitude of the maximum tolerated delay time in the early reservation connection request reflects the urgency of the early reservation connection request for spectrum resource allocation. Therefore, for the connection request to be reserved in advance, the high computing capacity and the storage capacity in the edge cloud computing network are utilized to allocate the spectrum resources existing in the network, and the spectrum resources are allocated to the connection request to be reserved in advance before the maximum tolerant delay time, so that the conditions of high blocking rate and low spectrum utilization rate caused by the arrival of the connection request which is increased rapidly in a short time in the network can be greatly improved.
Routing and spectrum allocation problems are core problems of the elastic optical network, and some routing, modulation and spectrum allocation methods for planning and provisioning in the elastic optical network already exist in the existing traditional network model. However, most of these routing and spectrum allocation methods, because of the lack of high computational power and node storage capacity in conventional networks, do not consider how to handle a large number of centralized, tolerable, low-latency connection requests, but only consider the case when a large number of immediate reservation connection requests are handled, i.e., they are allocated spectrum resources immediately upon arrival. However, these connection requests do not need to be serviced immediately upon arrival and occupy spectrum resources, which also results in a waste of spectrum resources. Therefore, the advance reservation class connection requests can be further divided according to the maximum tolerated delay of different connection requests. According to the characteristic of different connection requests, more reasonable network resource allocation can be made in the edge cloud computing elastic optical network.
Conventional resilient optical networks exhibit limitations in allocating spectrum resources for connection requests while handling a large number of different types of connection requests. Most existing networks fail to guarantee tolerable low latency services while handling large numbers of connection requests. With the rapid development of edge cloud computing and data centers, it becomes more and more important to improve the spectrum utilization rate and transmission efficiency of the elastic optical network. In order to improve network performance, edge cloud computing and an elastic optical network can be combined to provide more reliable and efficient network service quality. In an edge cloud computing network, connection requests may be offloaded to the edge computing network to reduce the computational pressure of the central network. On the other hand, the edge cloud computing network has higher computing capacity and moderate response time, and can meet the low-delay requirement of the connection request. These connection requests with zero initial delay tolerance are called immediate reservation connection requests because they need to be served immediately after arrival, and are blocked immediately if the network does not have sufficient spectrum resources available at that time. Another type of connection requests are pre-reservation connection requests that allow some initial delay during the establishment of the connection, as long as the spectrum resources are allocated before the maximum tolerated delay. However, when a huge connection request arrives, the prior art cannot make a reasonable spectrum resource allocation plan according to different connection request types such as urgency, and the like, thereby causing high blocking and affecting network resource utilization rate and network performance.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to overcome the defects in the prior art, and provide a method and a system for maximum tolerant delay reallocation of an elastic optical network for edge cloud computing, which can effectively improve the resource utilization rate of the network and reduce the blocking rate of the network when a huge connection request arrives in the network.
In order to solve the technical problem, the invention provides a maximum tolerant delay redistribution method for an elastic optical network of edge cloud computing, which comprises the following steps:
constructing and initializing an edge cloud computing elastic optical network model, generating a connection request, and classifying the connection request according to the emergency degree according to the maximum tolerant delay time of the connection request;
establishing a candidate transmission path set of a connection request, calculating the number of required frequency spectrum slots of the connection request on each candidate path, and performing priority ordering on the candidate paths;
and distributing network resources by combining edge cloud computing, searching the number of idle required frequency spectrum slots on the candidate path according to the priority sequence and the classification type of the connection request, and establishing the connection request after the searching is successful.
In an embodiment of the present invention, the edge cloud computing elastic optical network model is: g (N) e ,N c ,N o ,E,D st S), in which N e 、N c 、N o Respectively representing the aggregation of edge nodes, cloud nodes and optical switching nodes in the network, E representing optical fiber links, S representing each optical fiber linkNumber of available spectrum slots, D st From the set N e 、N c 、N o A set of physical distances between each pair of adjacent nodes in (a).
In one embodiment of the invention, each of the connection requests CR is CR (s, d, C, t) a ,td max ,H t ) Where s denotes a source node of the connection request, d denotes a destination node of the connection request, C denotes a connection request capacity size, t a Is the arrival time of the connection request, td max Is the maximum tolerated delay time of the connection request, H t Is the hold time of the connection request.
In one embodiment of the invention, the required number of spectrum slots N S The calculation method comprises the following steps:
where C represents the connection request capacity size, F is the modulation class determined according to the path, C slot Is the bandwidth capacity of a single spectrum slot at the corresponding modulation level, and GB is the number of spectrum slots of the guard bandwidth.
In an embodiment of the present invention, the prioritizing the candidate paths specifically includes:
multiplying the required frequency spectrum slot number of the connection request on each candidate path by the node number on each candidate path, and carrying out priority ordering on the candidate transmission paths according to the size of the product result.
In an embodiment of the present invention, when the network resources are allocated in combination with edge cloud computing, and the number of idle required spectrum slots is searched on a candidate path according to a priority order and a classification type of a connection request, if there is no available idle required spectrum slot number on all candidate paths, spectrum resources required by other connection requests in a current network are allocated first through storage and computing capabilities of an edge node and a cloud node, and then idle spectrum resources released by whether there are other connection requests due on a candidate transmission path are searched within a maximum tolerance time of a cached service.
In an embodiment of the present invention, the classifying the connection request according to the maximum tolerable delay time of the connection request according to the urgency degree specifically includes:
and taking the connection request with the maximum tolerant delay time of 0 as an instant reservation connection request, and taking the connection request with the maximum tolerant delay time of 0 as an advance reservation connection request.
In an embodiment of the present invention, the searching for the number of idle required spectrum slots on the candidate path according to the priority order and the classification type of the connection request specifically includes:
s1: searching whether the candidate transmission path has the number of idle required frequency spectrum slots according to the priority sequence, if so, allocating resources to the connection request, and successfully establishing the connection; if not, executing S2;
s2: judging the type of the connection request, if the connection request is an instant reservation connection request, judging the connection request as blocking; if the connection request is a pre-reserved connection request, executing S3;
s3: after waiting time, searching whether the candidate transmission path has the number of idle required frequency spectrum slots or not according to the priority sequence, if so, allocating resources to the connection request, and successfully establishing the connection; if not, executing S4;
s4: and S3, stopping searching until the total elapsed waiting time reaches the maximum tolerant delay time of the connection request, and judging the connection request as blocking.
The invention also provides a system for redistributing the maximum tolerant delay of the elastic optical network of the edge cloud computing, which comprises a network initialization module, a connection request generation module, a spectrum resource computing module and a spectrum resource distributing module,
the network initialization module acquires network topology information and initializes the edge cloud computing elastic optical network parameters;
the connection request generation module randomly selects a source node and a destination node of a connection request to generate the connection request;
the frequency spectrum resource calculation module establishes a candidate transmission path set of the connection request, and calculates the number of required frequency spectrum slots of the connection request on each candidate path;
the spectrum resource allocation module performs priority ordering on the candidate paths, allocates network resources by combining edge cloud computing, searches the number of idle required spectrum slots on the candidate paths according to the priority order and the classification type of the connection request, and establishes the connection request after the search is successful.
In one embodiment of the invention, the system further comprises a resource releasing module and a network state monitoring module,
the resource releasing module releases the spectrum resources occupied by the working path after the connection request is successfully transmitted, releases the computing resources of the edge computing server for processing the connection request, and clears the working path information established by the connection request;
the network state monitoring module is used for monitoring the working states of the network initialization module, the connection request generation module, the spectrum resource calculation module, the spectrum resource allocation module and the resource release module in real time and acquiring the real-time state of successful connection request establishment or network blockage.
Compared with the prior art, the technical scheme of the invention has the following advantages:
according to the invention, the connection requests are classified according to the emergency degree, and spectrum slot resources are distributed by combining the required spectrum slot number of the connection requests calculated by establishing the candidate transmission path and the edge cloud calculation, so that the resource utilization rate of the network can be effectively improved when a huge connection request arrives in the network, and the blocking rate of the network is reduced.
Drawings
In order that the present disclosure may be more readily and clearly understood, reference is now made to the following detailed description of the present disclosure taken in conjunction with the accompanying drawings, in which:
figure 1 is a flow chart of the method of the present invention,
figure 2 is a detailed flow chart of a method in an embodiment of the invention,
figure 3 is a block diagram of the architecture of the system of the present invention,
figure 4 is a diagram of the NSFNet network topology in an embodiment of the invention,
FIG. 5 is a block diagram of an embodiment of the present invention for handling an instant reservation connection request CR 1 A schematic diagram of the time link spectrum occupation state,
FIG. 6 is a block diagram illustrating an example of a CR apparatus for handling an early reservation connection request in an embodiment of the present invention 2 And (3) a time link spectrum occupation state diagram.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
Referring to fig. 1-2, the invention discloses a maximum tolerant delay reallocation method for an elastic optical network of edge cloud computing, and for a connection request to be reserved in advance, different maximum tolerant delay times also represent the priority degree of the connection request for obtaining network resource allocation. Firstly, generating connection requests with different maximum tolerance delays, instantly reserving the connection requests when the maximum tolerance delay is 0, and reserving the connection requests in advance when the maximum tolerance delay is not 0. And establishing a working path for each connection request by using K shortest path algorithms, finding an available frequency slot range on each link, allocating spectrum resources according to the arrival time, and if the connection request is blocked, performing secondary allocation on the advance reservation connection request with the maximum tolerant delay. The method specifically comprises the following steps:
step 1: constructing and initializing an edge cloud computing elastic optical network model; the edge cloud computing elastic optical network model is G (N) e ,N c ,N o ,E,D st S), in which N e 、N c 、N o Respectively representing the aggregation of edge nodes, cloud nodes and optical switching nodes in the network, E representing a group of optical fiber links, S representing the number of available spectrum slots in each optical fiber link, and D st From the set N e 、N c 、N o A set of physical distances between each pair of adjacent nodes in the cluster; for example, D st (i, j) is the actual distance between node i and node j in the network.
Step 2: generating a set of connection requests; when tolerable delay times are not considered, the designated network operates according to the time of arrival size. The connection requests are classified according to their maximum tolerated delay time.
Step 2-1: each of the connection requests CR is 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 connection request capacity, t a Is the time of arrival of the connection request, td max Is the maximum tolerated delay time of the connection request, H t Is the hold time of the connection request. The connection request arrival time follows the poisson process and the connection request hold time follows a negative exponential distribution. For each instant reservation connection request, their maximum tolerated delay time is 0, which is generated uniformly within a reasonable range of time for each advance reservation connection request.
Step 2-2: the connection request which is required to be processed as soon as the maximum tolerant delay time of the connection request is 0, namely the connection request arrives, is taken as an instant reservation connection request, and the connection request which is not required to be processed immediately, namely the connection request arrives, is taken as an advance reservation connection request, wherein the maximum tolerant delay time of the connection request is not 0. The urgency of the connection request to the spectrum resource allocation is judged by sensing the maximum tolerant delay time of different connection requests, more reasonable network resource allocation is carried out, and better network performance improvement is realized in the aspects of blocking rate and spectrum occupancy rate.
And step 3: the candidate transmission path set of the connection request is established, in this embodiment, when a certain connection request CR (s, d, C, t) a ,td max ,H t ) When the path belongs to CR, K shortest path algorithms are used for selecting K available candidate paths from the source node s to the destination node d.
And 4, step 4: and calculating the number of required frequency spectrum slots of the connection request on each candidate path in the candidate transmission path set, and carrying out priority ordering on the candidate paths.
Step 4-1: judging whether the candidate transmission path set is empty or not, if the candidate transmission path set is empty, indicating that the path establishment fails, judging the connection request as blocking; if the candidate transmission path set is not empty, indicating that the path establishment is successful, calculating the number N of required frequency spectrum slots of the connection request on each candidate path in the candidate transmission path set S Comprises the following steps:
where C represents the connection request capacity size, F is the modulation class determined according to the path, C slot Is the bandwidth capacity of a single spectrum slot at the corresponding modulation level, and GB is the number of spectrum slots of the guard bandwidth. The bandwidth capacity of a single spectrum slot may be expressed as F.C slot Gb/s, F is 1, 2, 3 and 4 for BPSK, QPSK, 8-QAM and 16-QAM, respectively. The required number of spectrum slots N for selecting different routing paths for the same connection request S May be different. Therefore, in the routing and spectrum allocation problem, the appropriate modulation format is selected for the arriving connection request according to the selection criteria of table 1, taking into account the physical distance between adjacent nodes; calculating N according to modulation format by formula (1) S 。
Table 1 table of selection criteria between modulation formats and physical distances between candidate paths
| Physical distance | Selection criteria |
| Transmission distance 3000KM-6000KM | BPSK (M = 1) |
| Transmission distance 1500KM-3000KM | QPSK (M = 2) is selected for use |
| Transmission distance 750KM-1500KM | Selecting 8-QAM (M = 3) |
| Transmission distance 0KM-750KM | Selecting 16-QAM (M = 4) |
Step 4-2: multiplying the required frequency spectrum slot number of the connection request on each candidate path and the node number on each candidate path, and carrying out priority ordering on the candidate transmission paths according to the size of the product result.
And 5: and distributing network resources by combining edge cloud computing, searching the number of idle required frequency spectrum slots on the candidate path according to the priority order and the classification type of the connection request, and establishing the connection request after the searching is successful.
When the number of the idle required spectrum slots is searched on the candidate path, if the number of the idle required spectrum slots is unavailable on all the candidate paths, the spectrum resources required by other connection requests in the current network are firstly distributed through the storage and computing capabilities of the edge nodes and the cloud nodes, and then the idle spectrum resources released by whether other connection requests expire or not on the candidate transmission path are searched within the maximum tolerance time of the cached service. The free spectrum slots on the candidate path need to satisfy both spectrum coherence and spectrum continuity to be available.
Step 5-1: searching whether the candidate transmission path has the number of idle required frequency spectrum slots according to the priority sequence, if so, allocating resources to the connection request, and successfully establishing the connection; if not, go to step 5-2.
Step 5-2: judging the type of the connection request, if the connection request is an instant reservation connection request, judging the connection request as blocking; and if the connection request is the pre-reserved connection request, executing the step 5-3.
Step 5-3: after waiting time, searching whether the candidate transmission path has the number of idle required frequency spectrum slots or not according to the priority sequence, if yes, allocating resources to the connection request, and successfully establishing the connection; if not, executing step 5-4; the value of the waiting time ts is set according to the actual situation, and the duration is less than the maximum tolerant delay time td of the connection request max 。
Step 5-4: and 5-3, stopping searching until the total elapsed waiting time reaches the maximum delay tolerance time of the connection request, and judging the connection request as blocking.
The method of the invention can effectively reduce high blocking caused by massive connection requests and improve the problem of low spectrum utilization rate of the traditional optical network by processing data at the network edge and combining network resource allocation of edge cloud computing.
As shown in fig. 3, the present invention also discloses a system for redistributing maximum tolerable delay of an elastic optical network in edge cloud computing, which includes the following modules:
(1) A network initialization module: acquiring network topology information, and initializing edge cloud computing elastic optical network parameters; initializing the connection state of optical network links, the number of node computing resources, the number of network switching nodes, the number of optical fiber links and the bandwidth size of each frequency spectrum slot.
(2) A connection request generation module: randomly selecting a source node and a destination node of a connection request to generate the connection request; the connection request arrival time follows the poisson process and the connection request hold time follows a negative exponential distribution. For each instant reservation connection request, their maximum tolerated delay time is 0, which is generated uniformly within a reasonable range of time for each advance reservation connection request.
(3) A spectrum resource calculation module: the calculation module establishes a candidate transmission path set of the connection request and calculates the number of required frequency spectrum slots of the connection request on each candidate path; the spectrum resource calculation module comprises a route calculation and modulation format selection module which calculates K pieces of standby time by using a K piece shortest path algorithmAnd selecting the path, storing the corresponding K candidate paths, and establishing a routing path for the connection request in sequence. Selecting a corresponding appropriate modulation format for each routing path according to the physical distance between adjacent nodes, and calculating the required number N of spectrum slots of the connection request on each candidate path according to the modulation format by the spectrum resource calculation module S 。
(4) A spectrum resource allocation module: and carrying out priority sequencing on the candidate paths, distributing network resources by combining edge cloud computing, searching the number of idle required frequency spectrum slots on the candidate paths according to the priority sequence and the classification type of the connection request, and establishing the connection request after the searching is successful. According to the connection request CR (s, d, C, t) a ,td max ,H t ) Calculating the required number of spectral gaps N S When the spectrum resources required by meeting the connection request are searched in the selected working path, if dual constraint conditions of spectrum continuity and spectrum consistency are met at the same time, the connection request is successfully established; and if the dual constraint conditions of the spectrum continuity and the spectrum consistency cannot be simultaneously met, the connection request is failed to be established. For an instant reservation connection request, reporting that the connection request is blocked when there is no available spectrum resource. When the connection request is reserved in advance, if the current network has insufficient available spectrum resources available for use, the connection request is buffered, whether available resources are allocated to the connection request reserved in advance is found out in the maximum tolerable delay time, and if enough network spectrum resources generated due to the release of the connection request are allocated in the maximum tolerable delay time, spectrum resources are allocated to the connection request reserved in advance.
(5) A resource release module: after the connection request is transmitted successfully, the spectrum resource occupied by the working path is released, the computing resource of the edge computing server for processing the connection request is released, and the working path information established by the connection request is cleared.
(6) A network state monitoring module: and acquiring the real-time state of successful establishment of the connection request or network blockage for monitoring the working states of the network initialization module, the connection request generation module, the spectrum resource calculation module, the spectrum resource allocation module and the resource release module in real time.
(7) A judgment and early warning module: and executing a coordination function among the modules, and judging and early warning whether each module is established successfully, so as to fulfill the aims of routing, spectrum allocation and spectrum resource allocation in the edge cloud computing elastic optical network and improve the transmission performance of the network.
(8) A network performance evaluation module: and after all the connection requests are processed, evaluating the performance parameters of the network according to the number of the spectrum resources used in the whole network, the successful establishment of the connection requests or the blocking state of the network.
The invention can process the network resource allocation problem when a large number of instant reservation connection requests exist in a short time in the network and the connection requests are reserved in advance, and the two connection requests are different in type. By defining the maximum delay tolerance time of the connection request, the system can sense the urgency degree of different connection requests for network spectrum resource allocation, and therefore more reasonable spectrum allocation selection is made. The edge cloud computing is combined with the traditional elastic optical network, and more reliable and efficient network service is provided.
According to the invention, network congestion caused by a huge amount of connection requests can be effectively reduced by processing data at the network edge and combining network resource allocation of edge cloud computing.
The invention fully utilizes the computing capability and the node storage capability of the edge node and the cloud node in the elastic optical network to process a large amount of centralized and tolerable low-delay connection requests. The situation of processing a large number of instant reservation and reserving connection requests in advance is considered, the situation that some connection requests are not required to be served immediately and occupy frequency spectrum resources when arriving is avoided, and the waste of the frequency spectrum resources is reduced.
The invention further considers that a group of connection requests are reserved in advance, the maximum tolerance delay time of the connection requests is different according to different served requirements of specific connection requests, and more reasonable network resource allocation can be continuously made through the characteristic of the connection requests, thereby further improving the network performance.
To further illustrate the beneficial effects of the present invention, experiments were conducted in the network topology shown in fig. 4 in this example. Fig. 4 is a NSFNet (wide area network with three-level hierarchy) network topology of the network, where the unit of link distance in fig. 4 is km, there are 14 nodes, and 21 bidirectional links, and the number on the optical fiber link indicates the length of the link, and the bandwidth of each spectrum slot is set to be 12.5GHz, and the capacity of the optical fiber link is 80 spectrum slots. The capacity range C for generating the connection request is 12.5-200Gb/s, and different modulation formats are respectively used.
For connection request CR (s, d, C, t) a ,td max ,H t ) Assuming that a connection request CR1 (2,11,100,5.5696,0, 62.9133) K =3 is generated, this connection request s =2, d =11, c =100gb/s, t = a ＝5.5696,td max ＝0,H t =62.9133, the working path 2-5-12-11 has been selected, the modulation level F =2 is selected, the number of spectrum slots of the guard bandwidth is GB =1, and the number of spectrum slots used for calculation is GB =1
This connection request is an instant reservation connection request, and when connection request CR1 (2,11,100,5.5696,0, 62.9133) arrives, the spectrum occupancy state in the selected path is shown in fig. 5, where the grey color indicates that the spectrum slot is occupied and the remaining blank spaces represent free available spectrum slots. At the moment of arrival of the connection request, there are not enough available spectrum resources in the network, and the instant reservation connection request CR1 (2,11,100,5.5696,0, 62.9133) is immediately blocked. For the advance reservation connection request CR2 (2,11,100,6.44382,2.41556,35.9462), it can be seen that for CR2 (2,11,100,6.44382,2.41556,35.9462), except for arrival time t a Maximum tolerated delay time td max And a retention time H t The remaining parameters are consistent with CR1 (2,11,100,5.5696,0, 62.9133). With respect to the timely reservation of the connection request CR1 (2,11,100,5.5696,0, 62.9133), the spectrum resources not available for the current link meet the continuity and consistency of the connection request, which may result in network congestion. However, for the pre-reservation connection request CR2 (2,11,100,6.44382,2.41556,35.9462), with a certain tolerable delay time, the allocation of network resources can be done using secondary allocation to improve network utilizationThe performance of the service. As shown in fig. 6, the advance reservation connection request CR2 (2,11,100,6.44382,2.41556,35.9462) requires 5 consecutive frequency slots. Due to insufficient bandwidth resources, the connection request cannot be provided immediately. The connection request does not immediately report blocking, and it is found by network allocation that the connection request currently occupying spectrum resources is released before the maximum delay tolerance time of CR2 (2,11,100,6.44382,2.41556,35.9462), and sufficient available spectrum resources are generated for CR2 (2,11,100,6.44382,2.41556,35.9462). By observing the spectrum occupation state of the routing path, t = t is found s +t 1 At that point, the spectrum resources reserved for CR2 (2,11,100,6.44382,2.41556,35.9462) in link 2-5 are released. At t = t s +t 2 At that time, a portion of the spectrum resources of links 5-12 and 12-11 are also released. Finally at t = t s +td max At that moment, the available spectrum resources in the link are sufficiently allocated to the pre-reservation connection request CR2 (2,11,100,6.44382,2.41556,35.9462), where t 1 ＜t 2 ＜td max The advance reservation connection request CR2 (2,11,100,6.44382,2.41556,35.9462) completes the reallocation. If it is found by the allocation that there are still not enough spectrum resources available, then CR2 (2,11,100,6.44382,2.41556,35.9462) reports are blocked.
The invention considers the network resource allocation, and defines the blocking probability BP of service supply as follows:
wherein, CR r Is the number of blocked connection requests, CR, caused by insufficient spectrum resources on the first stage optical fiber link s Is the number of successful connection requests to reallocate network resources in the second phase and CR is the total number of all connection requests. Compared with the blocking probability BP obtained by the traditional method without service type sensing and secondary distribution, the blocking probability BP obtained in the experiment obtains lower blocking rate and higher spectrum occupancy rate, and proves the beneficial effects of the invention.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications of the invention may be made without departing from the scope of the invention.
Claims (10)
1. A maximum tolerant delay reallocation method for an elastic optical network of edge cloud computing is characterized by comprising the following steps:
constructing and initializing an edge cloud computing elastic optical network model, generating a connection request, and classifying the connection request according to the emergency degree according to the maximum tolerant delay time of the connection request;
establishing a candidate transmission path set of a connection request, calculating the number of required frequency spectrum slots of the connection request on each candidate path, and performing priority ordering on the candidate paths;
and distributing network resources by combining edge cloud computing, searching the number of idle required frequency spectrum slots on the candidate path according to the priority order and the classification type of the connection request, and establishing the connection request after the searching is successful.
2. The edge cloud computing elastic optical network maximum delay tolerant reallocation method of claim 1, wherein: the edge cloud computing elastic optical network model comprises: g (N) e ,N c ,N o ,E,D st S), in which N e 、N c 、N o Respectively representing the aggregation of edge nodes, cloud nodes and optical switching nodes in the network, E representing optical fiber links, S representing the number of available spectrum slots in each optical fiber link, and D st From the set N e 、N c 、N o A set of physical distances between each pair of adjacent nodes in (a).
3. The elastic optical network maximum tolerant delay reallocation method of edge cloud computing according to claim 1,the method is characterized in that: each of the connection requests CR is 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 connection request capacity, t a Is the time of arrival of the connection request, td max Is the maximum tolerated delay time of the connection request, H t Is the hold time of the connection request.
4. The edge cloud computing elastic optical network maximum delay tolerant reallocation method of claim 1, wherein: the number N of required frequency spectrum slots S The calculation method comprises the following steps:
where C represents the connection request capacity size, F is the modulation class determined according to the path, C slot Is the bandwidth capacity of a single spectrum slot at the corresponding modulation level, and GB is the number of spectrum slots of the guard bandwidth.
5. The edge cloud computing elastic optical network maximum delay tolerant reallocation method of claim 1, wherein: the priority ranking of the candidate paths specifically includes:
multiplying the required frequency spectrum slot number of the connection request on each candidate path and the node number on each candidate path, and carrying out priority ordering on the candidate transmission paths according to the size of the product result.
6. The elastic optical network maximum-tolerant delay reallocation method of edge cloud computing according to claim 1, wherein: and when the number of idle required spectrum slots is searched on the candidate path according to the priority order and the classification type of the connection request, if the number of the idle required spectrum slots does not exist on all the candidate paths, the network resources required by other connection requests in the current network are firstly allocated through the storage and computing capabilities of the edge nodes and the cloud nodes, and then idle spectrum resources released by whether other connection requests expire or not are searched on the candidate transmission path within the maximum tolerance time of the cached service.
7. The elastic optical network maximum tolerant delay reallocation method of edge cloud computing according to any of claims 1-6, wherein: the method for classifying the connection requests according to the maximum tolerant delay time of the connection requests comprises the following steps:
and taking the connection request with the maximum tolerant delay time of 0 as an instant reservation connection request, and taking the connection request with the maximum tolerant delay time of 0 as an advance reservation connection request.
8. The edge cloud-computing elastic optical network maximum-tolerant delay reallocation method of claim 7, wherein: the searching for the number of the idle required frequency spectrum slots on the candidate path according to the priority order and the classification type of the connection request specifically comprises:
s1: searching whether the candidate transmission path has the number of idle required frequency spectrum slots according to the priority sequence, if so, allocating resources to the connection request, and successfully establishing the connection; if not, executing S2;
s2: judging the type of the connection request, if the connection request is an instant reservation connection request, judging the connection request as blocking; if the connection request is a pre-reserved connection request, executing S3;
s3: after waiting time, searching whether the candidate transmission path has the number of idle required frequency spectrum slots or not according to the priority sequence, if so, allocating resources to the connection request, and successfully establishing the connection; if not, executing S4;
s4: and S3, stopping searching until the total elapsed waiting time reaches the maximum tolerant delay time of the connection request, and judging the connection request as blocking.
9. An edge cloud computing elastic optical network maximum tolerant delay redistribution system, characterized in that: comprises a network initialization module, a connection request generation module, a spectrum resource calculation module and a spectrum resource allocation module,
the network initialization module acquires network topology information and initializes the edge cloud computing elastic optical network parameters;
the connection request generation module randomly selects a source node and a destination node of a connection request to generate the connection request;
the spectrum resource calculation module establishes a candidate transmission path set of the connection request and calculates the number of required spectrum slots of the connection request on each candidate path;
the spectrum resource allocation module performs priority ordering on the candidate paths, allocates network resources by combining edge cloud computing, searches the number of idle required spectrum slots on the candidate paths according to the priority order and the classification type of the connection request, and establishes the connection request after the search is successful.
10. The edge cloud computing resilient optical network maximum tolerated delay redistribution system of claim 9, wherein: also comprises a resource releasing module and a network state monitoring module,
the resource releasing module releases spectrum resources occupied by the working path after the connection request is transmitted successfully, releases computing resources of an edge computing server for processing the connection request, and clears working path information established by the connection request;
the network state monitoring module is used for monitoring the working states of the network initialization module, the connection request generation module, the spectrum resource calculation module, the spectrum resource allocation module and the resource release module in real time and acquiring the real-time state of successful connection request establishment or network blockage.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211346546.3A CN115914890A (en) | 2022-10-31 | 2022-10-31 | Elastic optical network maximum tolerant delay redistribution method and system based on edge cloud computing |
| PCT/CN2022/142174 WO2024092994A1 (en) | 2022-10-31 | 2022-12-27 | Reallocation method and system based on maximum tolerable delay in edge-cloud-computing-based elastic optical network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211346546.3A CN115914890A (en) | 2022-10-31 | 2022-10-31 | Elastic optical network maximum tolerant delay redistribution method and system based on edge cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115914890A true CN115914890A (en) | 2023-04-04 |
Family
ID=86495612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211346546.3A Pending CN115914890A (en) | 2022-10-31 | 2022-10-31 | Elastic optical network maximum tolerant delay redistribution method and system based on edge cloud computing |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115914890A (en) |
| WO (1) | WO2024092994A1 (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109245918A (en) * | 2018-08-20 | 2019-01-18 | 中天宽带技术有限公司 | The flexible optical-fiber network energy consumption optimization method of software definition frequency spectrum and its system |
| CN112866103A (en) * | 2021-01-12 | 2021-05-28 | 重庆大学 | Edge-calculation-oriented time-sensitive mobile forwarding network protection method |
| CN114116211A (en) * | 2021-11-22 | 2022-03-01 | 中通服咨询设计研究院有限公司 | Service flow distribution optimization method and system for mobile edge computing |
| CN114172962A (en) * | 2021-12-07 | 2022-03-11 | 大连海事大学 | Industrial AGV (automatic guided vehicle) -oriented bidirectional selection edge computing service distribution method |
| CN115118596A (en) * | 2022-07-13 | 2022-09-27 | 杭州师范大学 | Controller optimal deployment method and system based on bilateral matching |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104734957B (en) * | 2013-12-24 | 2018-03-23 | 中国移动通信集团公司 | Business transmitting method and device in a kind of software defined network SDN |
| CN107426110B (en) * | 2017-09-22 | 2020-06-05 | 苏州大学 | Adaptive load balancing energy consumption optimization method and system in spectrum flexible optical network |
| CN113742046A (en) * | 2021-09-17 | 2021-12-03 | 苏州大学 | Flow grooming cloud-side computing network computing resource balanced scheduling method and system |
| CN114302267B (en) * | 2021-12-14 | 2022-10-18 | 苏州大学 | Special protection spectrum allocation method and system for space division multiplexing optical network of data center |
-
2022
- 2022-10-31 CN CN202211346546.3A patent/CN115914890A/en active Pending
- 2022-12-27 WO PCT/CN2022/142174 patent/WO2024092994A1/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109245918A (en) * | 2018-08-20 | 2019-01-18 | 中天宽带技术有限公司 | The flexible optical-fiber network energy consumption optimization method of software definition frequency spectrum and its system |
| CN112866103A (en) * | 2021-01-12 | 2021-05-28 | 重庆大学 | Edge-calculation-oriented time-sensitive mobile forwarding network protection method |
| CN114116211A (en) * | 2021-11-22 | 2022-03-01 | 中通服咨询设计研究院有限公司 | Service flow distribution optimization method and system for mobile edge computing |
| CN114172962A (en) * | 2021-12-07 | 2022-03-11 | 大连海事大学 | Industrial AGV (automatic guided vehicle) -oriented bidirectional selection edge computing service distribution method |
| CN115118596A (en) * | 2022-07-13 | 2022-09-27 | 杭州师范大学 | Controller optimal deployment method and system based on bilateral matching |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024092994A1 (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022021176A1 (en) | Cloud-edge collaborative network resource smooth migration and restructuring method and system | |
| JP5324637B2 (en) | Dynamic flowlet scheduling system, flow scheduling method, and flow scheduling program | |
| WO2018072687A1 (en) | Resource scheduling method and apparatus, and filtered scheduler | |
| WO2023039965A1 (en) | Cloud-edge computing network computational resource balancing and scheduling method for traffic grooming, and system | |
| CN112269641B (en) | Scheduling method, scheduling device, electronic equipment and storage medium | |
| CN103812949B (en) | A kind of task scheduling towards real-time cloud platform and resource allocation methods and system | |
| CN111901170B (en) | Reliability-aware service function chain backup protection method | |
| CN113784373A (en) | Combined optimization method and system for time delay and frequency spectrum occupation in cloud edge cooperative network | |
| CN111246586A (en) | Method and system for distributing smart grid resources based on genetic algorithm | |
| JP2001077848A (en) | Band allocating method | |
| CN101127689B (en) | Method for minimizing priority seizing cost | |
| CN109743751B (en) | Resource allocation method and device for wireless access network | |
| CN107135056B (en) | Anycast service resource allocation method for reducing frequency spectrum fragments and time delay | |
| CN106817306B (en) | Method and device for determining target route | |
| WO2021136100A1 (en) | Cdn scheduling method and system, and device and storage medium | |
| CN112148381A (en) | Software definition-based edge computing priority unloading decision method and system | |
| WO2022166348A1 (en) | Routing method, routing apparatus, controller and computer-readable storage medium | |
| WO2017045640A1 (en) | Associated stream bandwidth scheduling method and apparatus in data center | |
| CN108616782B (en) | Frequency spectrum allocation method based on disjoint connection group optimization in elastic optical network | |
| CN112437449B (en) | Joint resource allocation method | |
| CN115914890A (en) | Elastic optical network maximum tolerant delay redistribution method and system based on edge cloud computing | |
| CN115562841B (en) | Cloud video service self-adaptive resource scheduling system and method | |
| CN109039717B (en) | Service resource management method and system | |
| CN114978913B (en) | Cross-domain deployment method and system for service function chains based on cut chains | |
| CN105187483A (en) | Method and device for allocating cloud computing resources |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |