CN113473266A - PTN transmission loop bandwidth utilization rate optimization method and device and computing equipment - Google Patents
PTN transmission loop bandwidth utilization rate optimization method and device and computing equipment Download PDFInfo
- Publication number
- CN113473266A CN113473266A CN202010245438.1A CN202010245438A CN113473266A CN 113473266 A CN113473266 A CN 113473266A CN 202010245438 A CN202010245438 A CN 202010245438A CN 113473266 A CN113473266 A CN 113473266A
- Authority
- CN
- China
- Prior art keywords
- graph
- loop
- optimization
- ptn
- bandwidth utilization
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
- H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
- H04Q11/0062—Network aspects
- H04Q11/0067—Provisions for optical access or distribution networks, e.g. Gigabit Ethernet Passive Optical Network (GE-PON), ATM-based Passive Optical Network (A-PON), PON-Ring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
- H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
- H04Q11/0062—Network aspects
- H04Q2011/0086—Network resource allocation, dimensioning or optimisation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
- H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
- H04Q11/0062—Network aspects
- H04Q2011/009—Topology aspects
- H04Q2011/0092—Ring
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention relates to the technical field of network management, and discloses a method, a device and a computing device for optimizing the bandwidth utilization rate of a PTN transmission loop, wherein the method comprises the following steps: PTN transmission loop data are obtained, and the PTN transmission loop data are preprocessed, so that a target optimization range of loop bandwidth utilization rate is obtained; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; and carrying out iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value. Through the mode, the embodiment of the invention can solve the problem of uneven distribution of the PTN capacity utilization rate in the existing network, realize global fine capacity expansion and reduce the cost of manpower and material resources of enterprises.
Description
Technical Field
The embodiment of the invention relates to the technical field of network management, in particular to a method and a device for optimizing the bandwidth utilization rate of a PTN transmission loop and computing equipment.
Background
Packet Transport Network (PTN) devices carry all 4G services, part of 2G services, and special line services of government and enterprise of a mobile communication Network, and are the core of mobile end networks and special lines of government and enterprise. Along with the development of mobile communication networks, the traffic of users is increased dramatically, so that on one hand, the increasing traffic using requirements of users are met, on the other hand, the cost is saved, and the traditional rough expansion mode is avoided.
The maintenance responsibility of the access layer PTN transmission loop is divided in counties, and the traditional loop bandwidth utilization rate optimization method has three types, namely, the first method is to upgrade a Gigabit Ethernet (GE) access ring into a 10GE ring and upgrade the converged 10GE ring to an 40/100GE ring in a ring network rate upgrading mode, so that the service bearing capacity is improved, and the ring network utilization rate is reduced. And secondly, adjusting the high-flow service to other light-load PTN looped networks or Optical Transport Networks (OTN) by analyzing the service bearing condition of the out-of-limit PTN looped network. Thirdly, part of services are allocated to a new PTN looped network to bear the load in a mode of overlapping the PTN looped networks, and therefore the utilization rate of the looped network bandwidth is reduced.
The three methods only pay attention to the local structure of the loop during optimization, are easy to fall into local optimal solution, lack of optimization of the loop with low utilization rate, and are difficult to improve the bandwidth utilization rate of the whole loop. The existing PTN transmission loop bandwidth utilization rate optimization method reduces the utilization rate of the looped network by means of superposing the PTN looped network on the out-of-limit loop or upgrading the rate capacity of the looped network, namely, the method achieves the aim by means of equipment capacity expansion, is simple and rough and has high cost-to-efficiency ratio, lacks effective utilization of spare resources of the existing network, and is difficult to continuously meet the increasing flow demand. The method of adjusting the high-traffic service to other light-load PTN looped networks or OTN load-bearing is too dependent on manual experience, lacks global analysis, and is easy to fall into local optimal solution, thereby causing frequent adjustment of service load-bearing.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide a method, an apparatus, and a computing device for optimizing a bandwidth utilization rate of a PTN transmission loop, which overcome or at least partially solve the above problems.
According to an aspect of the embodiments of the present invention, there is provided a method for optimizing a bandwidth utilization rate of a PTN transmission loop, the method including: PTN transmission loop data are obtained, and the PTN transmission loop data are preprocessed, so that a target optimization range of loop bandwidth utilization rate is obtained; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; and carrying out iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
In an optional manner, the preprocessing the PTN transmission loop data to obtain a target optimization range of loop bandwidth utilization includes: taking a district as a unit, and obtaining the average value eta of the bandwidth utilization rate of all loops by applying the following relational expression through a PTN loop flow analysis report form:
adjusting the target optimization range (a, b) of the loop bandwidth utilization ratio to be the average value eta of the loop bandwidth utilization ratio
In an optional manner, the preprocessing the PTN transmission loop data further includes: summing the busy hour average flow rate data of each port of the network element by taking the network element as a unit through a port bandwidth utilization rate report to obtain the busy hour average flow rate of the PTN network element; acquiring a sensitive site identifier through a PTN sensitive site report; construction feasibility constraints are obtained by comprehensively measuring the network element connection distance, the construction cost and natural geological factors.
In an optional manner, the creating a topology structure of a graph by using the PTN transmission loop data to generate a graph loop path set satisfying a first preset condition includes: abstracting PTN transmission loop data into a node and edge relation of a graph, and establishing a topological structure of the graph; abstracting a PTN loop into a graph loop path meeting the first preset condition; and adopting a random walk method based on a graph neural network, after selecting a sink node as a path head node each time, diffusing and searching a graph loop path meeting the first preset condition from the random start of the sink node to surrounding nodes until all nodes in the graph are included, and generating the graph loop path set.
In an optional manner, the obtaining a graph optimization objective function according to the target optimization range of the loop bandwidth utilization includes:
obtaining a graph optimization target mean from the target optimization range (a, b) of the loop bandwidth utilization
Optimizing a target mean from the graph
Defining graph optimization objective function
Wherein, PjIs a path in the set of graph loop paths,
is path PjJ is a positive integer.
In an optional manner, the iteratively optimizing the graph loop path set based on the graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value includes: calculating the graph optimization objective function values for the set of graph loop paths; if the graph optimization objective function value is determined to meet the second preset condition, returning the set of graph loop paths with the minimum graph optimization objective function value; if the graph optimization objective function value is determined not to meet a second preset condition, splitting and recombining paths in the graph loop path set to generate a new graph loop path set; iteratively calculating the graph optimization objective function value of the new set of graph loop paths until the graph optimization objective function value satisfies the second preset condition.
In an alternative manner, the second preset condition includes: the iteration times are greater than the maximum iteration optimization times Max _ times; or the variation value e of the graph optimization objective function value of the current iteration and the last iteration is less than or equal to the minimum variation value threshold emin(ii) a Or the graph optimization objective function value of the current iteration is less than or equal to the minimum value omega.
According to another aspect of the embodiments of the present invention, there is provided an apparatus for optimizing a bandwidth utilization rate of a PTN transmission loop, the apparatus including: the data acquisition unit is used for acquiring PTN transmission loop data, preprocessing the PTN transmission loop data and acquiring a target optimization range of loop bandwidth utilization rate; the graph generating unit is used for establishing a topological structure of a graph by the PTN transmission loop data and generating a graph loop path set meeting a first preset condition; the target function obtaining unit is used for obtaining a graph optimization target function according to the target optimization range of the loop bandwidth utilization rate; and the iterative optimization unit is used for performing iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
According to another aspect of embodiments of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the steps of the PTN transmission loop bandwidth utilization rate optimization method.
According to yet another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, the executable instruction causing the processor to perform the steps of the above-mentioned PTN transmission loop bandwidth utilization optimization method.
The embodiment of the invention obtains the target optimization range of the loop bandwidth utilization rate by obtaining the PTN transmission loop data and preprocessing the PTN transmission loop data; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; iterative optimization is carried out on the graph loop path set based on a graph neural network, the graph loop path set with the minimum graph optimization objective function value is obtained, a service model of a PTN transmission looped network can be analyzed from a global angle, local optimization is avoided, the design time of a traditional loop out-of-limit listing rectification scheme is shortened, the problem that the PTN capacity utilization rate of the existing network is not distributed uniformly can be effectively solved, global fine capacity expansion is achieved, and the cost of labor and material resources of an enterprise can be reduced.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a method for optimizing a bandwidth utilization rate of a PTN transmission loop according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an initialization graph loop path set of a PTN transmission loop bandwidth utilization optimization method according to an embodiment of the present invention;
fig. 3 is a diagram illustrating an example of a topology of a diagram of a method for optimizing bandwidth utilization of a PTN transmission loop according to an embodiment of the present invention;
fig. 4 is a diagram illustrating an application example of a method for optimizing bandwidth utilization of a PTN transmission loop according to an embodiment of the present invention;
fig. 5 is a diagram illustrating an example of an optimized target path set of a PTN transmission loop bandwidth utilization optimization method according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram illustrating an apparatus for optimizing bandwidth utilization of a PTN transmission loop according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 is a flowchart illustrating a method for optimizing a bandwidth utilization rate of a PTN transmission loop according to an embodiment of the present invention. The PTN transmission loop bandwidth utilization rate optimization method is mainly applied to a server. As shown in fig. 1, the method for optimizing the bandwidth utilization of the PTN transmission loop includes:
step S11: PTN transmission loop data are obtained, preprocessing is carried out on the PTN transmission loop data, and a target optimization range of loop bandwidth utilization rate is obtained.
In this embodiment of the present invention, acquiring PTN transmission loop data of any county from the integrated resource management system, that is, connection relationships between two ends of the adjacent PTN network element A, Z and network element attribute data includes: the PTN network element number, the PTN network element name, the PTN network element type (access, convergence and backbone), the PTN network element longitude and latitude, the PTN network element board card capacity and the PTN segment number.
The PTN looped network bandwidth utilization rate peak value continuous 7 balances reach more than 70%, and the loop needs to be listed and modified. In contrast, most of the loop bandwidth utilization rate in the existing network is less than 30%, and the overall bandwidth utilization rate is low. According to the traditional technical method, the loops with the bandwidth utilization rate of more than 70% and less than 30% are optimized to 30-70%, however, due to the fact that the bandwidth utilization rate of each district and county in each city is not distributed uniformly, for the districts and counties with the bandwidth utilization rate average value of 10-25%, due to the fact that the number of loops with high utilization rate is extremely small, the difference required by optimizing a large number of loops with low utilization rate to be more than 30% is difficult to balance, and the optimization target is difficult to achieve. According to the embodiment of the invention, a district is taken as a unit, the average bandwidth utilization rate of all loops in the district is obtained through the PTN loop flow analysis report, and the target range is properly reduced for the district with the average bandwidth utilization rate lower than 25%, so that the original target domain is mapped to the new target domain.
Specifically, a county is set to have N loops, and the county is taken as a unit, and the following relational expression is applied to obtain the average value eta of the bandwidth utilization rate of all loops through the PTN loop traffic analysis report:
The formula for adjusting the optimization objective according to the objective optimization range (a, b) is:
in this way, the target optimization range (a, b) of the loop bandwidth utilization is adjusted to be the target optimization range (a, b) of the loop bandwidth utilization according to the average value eta of the loop bandwidth utilization
In the embodiment of the invention, the busy hour average flow rate data of each port of the network element is summed by taking the network element as a unit through the port bandwidth utilization rate report to obtain the busy hour average flow rate of the PTN network element. Specifically, as shown in table 1, the busy hour average flow rate data in the receiving and transmitting directions of each port of the network element are summed, and the maximum value of the summation result in the receiving and transmitting directions is used as the busy hour average flow rate of the PTN network element. In the embodiment of the invention, the sensitive site identification is also obtained through the PTN sensitive site report.
TABLE 1PTN network element busy hour average flow calculation
In the embodiment of the invention, the construction feasibility of the path optimization result is also fully considered, and the construction feasibility constraint is obtained by comprehensively measuring the network element connection distance, the construction cost and natural geological factors. As shown in table 2, the construction feasibility constraints include: network element connection distance limitation, such as suburban: 800/1000 m, urban area: 500 m, limitation of newly added connection quantity of network elements, and elimination of non-connectable relations caused by geological factors such as roads, bridges, rivers and the like.
TABLE 2 construction feasibility constraints
Step S12: and establishing a topological structure of the graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition.
Specifically, in step S12, as shown in fig. 2, the method includes:
step S121: and abstracting the PTN transmission loop data into the node and edge relation of the graph, and establishing the topological structure of the graph.
In the topological structure of the graph, the PTN network element is converted into a graph sectionThe node attributes include: node identification, network element type (T value), PTN network element longitude and latitude, PTN network element board card capacity (A value), and PTN network element receiving and transmitting flow velocity larger value (f)X) Sensitive site identification (D value), etc. The node identifier may be a PTN network element number ID or a PTN network element Name. The edges of the graph represent the connection relationship between the PTN network elements, and can be divided into two types, namely physical connection (hard connection) and logical connection (soft connection or probabilistic connection), wherein the physical connection refers to the connection actually existing between the PTN network elements, and the logical connection refers to the condition that the PTN network elements can be connected within a certain distance range. The logic connection relation among the PTN network elements in the embodiment of the invention is converted into the optional edge of the graph. The attributes of the edge include: the distance between nodes, the PTN section number, the connection limit system and the like.
The node attributes are described as follows:
a: int type, which can be 1, 10, 20, 40;
fX: float type;
t: sting type, which is divided into J type, H type and G type, and respectively corresponds to access, convergence and backbone;
d: the bol type, 1 or 0, respectively corresponds to a sensitive station and a non-sensitive station.
And establishing a topological structure of the graph according to the acquired related data of the graph nodes and the edges, wherein the topological structure comprises generation of an adjacency matrix and a related attribute value matrix of the graph and the like.
Step S122: abstracting the PTN loop into a graph loop path meeting the first preset condition.
Specifically, according to the topology of the graph established in step S121, initialization of the loop path set is performed. According to the PTN transmission loop establishment, a PTN loop abstraction is defined as a graph loop path satisfying a first preset condition, where the first preset condition is that the following conditions a, b, c, d, and e are simultaneously satisfied, and the following description is made with reference to the topology structure of the graph shown in fig. 3:
a, the starting point and the end point of the graph loop path P are H-type nodes (aggregation nodes) with 2 attribute values D being 0; other nodes on the graph loop path P can only be class J nodes (access nodes), and the degree of each node satisfies: q is more than or equal to 2, wherein Q is an integer more than or equal to 2, preferably 3; the total number of nodes on the loop path P is equal to or less than M, M is a positive integer constant, preferably 12, and the ear-loop nodes and branch nodes described in conditions b and c do not count the total number of path nodes. As shown in fig. 3, the graph loop path P starts at h1, ends at h2, and has a total number of nodes of 6.
b, if an ear ring is arranged on the graph loop path P, the value A (the card capacity value) of the node on the ring is less than or equal to the value A of the node on the graph loop path P; if a graph loop path P includes R nodes with attribute value D equal to 1, the path should include 1 to R rings, the rings should include all nodes with attribute value D equal to 1, and the degree of the nodes can only be 2, and typical value of R is 1 or 2. As shown in FIG. 3, an ear ring h3-h5-h4 is present on the loop path P, and the value of A of the node h5 on the ring is less than or equal to the value of A of the node h 3.
c on the graph loop path P, besides the starting point and the end point, the middle node has a branch single node or a branch node chain, and the A attribute value of the node on the branch is less than or equal to the A value of the node on the upper link (the typical value of the A value of the branch node is 1). The node h6 on the graph loop path P shown in FIG. 3 has a branch single node h9, and the A value of the node h9 is equal to or less than the A value of the node h 6.
d, presetting the board card capacity A of the graph loop path P, and setting the busy hour average flow speed f of each network element on the graph loop path PxiThe number of PTN network elements contained in the graph loop path P is N, the head and tail nodes are H-type (convergent) nodes, the middle nodes are J-type (access) nodes, the serial number of the head node is 1, and the serial number of the tail node is N. Presetting a calculation formula of a loop bandwidth utilization rate eta:
e-graph loop path set
Including all nodes in an undirected graph, with class J nodes in a set of loop paths
Occurs only 1 time
In one of the paths of (1); the class H node may appear multiple times, may appear in
In multiple paths.
Step S123: and adopting a random walk method based on a graph neural network, after selecting a sink node as a path head node each time, diffusing and searching a graph loop path meeting the first preset condition from the random start of the sink node to surrounding nodes until all nodes in the graph are included, and generating the graph loop path set.
If the loop path is set
The method includes all nodes in the graph, namely, the nodes in the graph are covered, the initialization of the graph loop path set is completed, and the graph path set is returned.
Step S13: and obtaining a graph optimization objective function according to the target optimization range of the loop bandwidth utilization rate.
Since the target optimization range varies with the variation of the average bandwidth utilization of the loop, in the embodiment of the present invention, the graph optimization target mean is obtained according to the target optimization ranges (a, b) of the loop bandwidth utilization
Wherein a is the lower limit of the target optimization range, and b is the upper limit.
Then optimizing the target mean from the graph
Defining graph optimization objective function
Wherein, PjIs in the set of loop paths of the graphIs detected by the optical sensor (c) and is,
is path PjJ is a positive integer. The aim of the embodiment of the invention is to find an optimal loop path set
So that the graph optimization objective function E is globally minimized.
Step S14: and carrying out iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
In the embodiment of the invention, the loop path set of the initialization graph is obtained firstly
I.e., the set of graph loop paths acquired in step S12
Then calculating the graph optimization objective function value of the graph loop path set; if the graph optimization objective function value is determined to meet the second preset condition, returning the set of graph loop paths with the minimum graph optimization objective function value; if the graph optimization objective function value is determined not to meet a second preset condition, splitting and recombining paths in the graph loop path set to generate a new graph loop path set; iteratively calculating the graph optimization objective function value of the new set of graph loop paths until the graph optimization objective function value satisfies the second preset condition.
The second preset condition includes: the iteration times are greater than the maximum iteration optimization times Max _ times; or the graph optimization objective function values of the current iteration and the last iteration
Is less than or equal to a minimum variance threshold eminI.e. e.ltoreq.emin(ii) a Or the graph of the current iterationThe value of the optimization objective function being less than or equal to the minimum value omega, i.e.
If the second preset condition is satisfied, any one of the three conditions may be satisfied. Wherein the graph optimizes the objective function values
Change value of
m represents the mth iteration, and (m-1) represents the previous iteration of the mth iteration. The parameter Max _ times, eminAnd omega are algorithm adjustable parameters and are used for reflecting whether iterative computation converges and controlling the end condition of the iterative computation, and corresponding values can be set according to the requirements of actual application scenes.
If the graph optimization objective function value does not meet the second preset condition, according to the descending gradient of the graph optimization objective function in the graph neural network and the limiting condition of the inter-node connecting edge, specifically the probability of the inter-node connecting edge, the loop path set of the graph is subjected to
The paths in the graph are split and recombined to generate a new graph loop path set
If the graph optimization objective function value meets the second preset condition, the iterative computation is ended, and the current graph optimization objective function value is returned
Set of minimum corresponding loop paths of the graph
Through the iterative computation process, a graph loop path set with a global minimum graph optimization objective function value is finally generated
Used for the design of the rectification scheme.
The embodiment of the invention abstracts the topological structure of the PTN transmission loop into the topological structure of the graph in the data structure, and optimizes the bandwidth utilization rate of the PTN transmission loop based on the graph optimization theory. The nodes of the graph represent PTN network elements, the edges of the graph represent the connection relation between the network elements, and the optimization of the bandwidth utilization rate of the whole PTN transmission loop is converted into the optimization of the minimum value of the whole objective function of the graph structure. By introducing the neural network, the complementation of bandwidth utilization rate between busy and idle loops is fully considered, and the capacity management mode of the traditional transmission loop is changed. Compared with the traditional method for adjusting the high-flow service to other light-load PTN looped networks or OTN bearing, the embodiment of the invention analyzes the service model of the PTN transmission looped network from the global angle, avoids falling into local optimization, reduces the design time of the traditional loop out-of-limit listing rectification scheme, and can effectively solve the problems of uneven distribution of the PTN capacity utilization rate and rough capacity expansion mode of the current network, thereby reducing the cost of labor and material resources of enterprises and having certain economic value of the enterprises.
The complete PTN transmission loop bandwidth utilization optimization process of the embodiment of the present invention is shown in fig. 4, and includes:
step S100: and starting.
Step S101: PTN transmission loop data is obtained.
And PTN transmission loop data of any county are obtained from the comprehensive resource management system, wherein the PTN transmission loop data comprise the connection relation and the network element attribute data of two ends of the adjacent PTN network element A, Z.
Step S102: and preprocessing the acquired PTN transmission loop data.
The method specifically comprises the steps of obtaining the average value of the loop bandwidth utilization rate of each county through a PTN loop flow analysis report, and obtaining the sensitive site identification through a PTN sensitive site report.
Step S103: and setting limiting parameters.
The construction feasibility of the path optimization result is fully considered, three constraint conditions of network element connection distance, construction cost and natural geological factors are comprehensively measured, and construction feasibility constraints are increased, wherein the three constraint conditions comprise: the method comprises the following steps of limiting the network element connection distance (such as 800/1000 meters in suburbs and 500 meters in urban areas), limiting the newly added connection quantity of network elements, and eliminating the non-connectable relation caused by geological factors such as roads, bridges and rivers.
Step S104: and adjusting the target optimization range of the loop bandwidth utilization rate.
The optimization target range (a, b) is adjusted from (30%, 70%) to
Step S105: generating a graph topology.
The network elements are converted into graph nodes, edges of the graph represent connection relations between the network elements and are divided into physical connection (hard connection) and logical connection (soft connection or probability connection), the physical connection refers to connection really existing between the network elements, and the logical connection refers to connection conditions within a certain distance range. The node attributes include: the node identification (PTN network element number ID, PTN network element Name), the network element type (T value), the PTN network element longitude and latitude, the PTN network element board card capacity (A value), the larger PTN network element receiving and transmitting flow rate value (f _ X), the sensitive station identification (D value) and the like. The attributes of the edge include: the distance between nodes, the PTN section number, the connection limit system and the like.
Step S106: and initializing a loop path set of the graph.
A random walk method based on a graph neural network is adopted, after an H-type (aggregation) node is selected as a path head node each time, a loop path meeting path conditions is searched for in a diffusion mode from the node in a random starting mode to surrounding nodes, and a graph loop path set is formed. If the loop path is set
The method includes all nodes in the graph, namely, the nodes in the graph are covered, the initialization of the graph loop path set is completed, and the graph loop path set is returned. The initialized set of graph loop paths is shown in Table 3, and includes two paths.
TABLE 3 initialized graph Loop Path set
| Serial number | S_paths | S_paths_fp |
| 1 | [A,B,C,D,E,F] | 27.20％ |
| 2 | [A,W,R,T,Y,U,F] | 50.40％ |
Step S107: and calculating a graph optimization objective function value.
According to the relational expression
Optimizing objective function values E, P by using a calculation mapjIs that
The path of (a) is selected,
is path PjThe utilization rate of the bandwidth is increased,
the mean value of the optimization objective is represented,
suppose the target optimization range is (a, b), a is the lower limit of the optimization range, and b is the upper limit.
Step S108: and judging whether the graph optimization objective function value or the iteration number meets a second preset condition. If yes, go to step S110; if not, step S109 is performed.
The second preset condition is that the graph optimization objective function value of the current iteration and the last iteration is satisfied, and the iteration number is larger than the maximum iteration optimization number set value Max _ times
Is less than or equal to a minimum variance threshold eminAnd one of the figure optimization objective function values of the current iteration is less than or equal to the minimum value omega.
Step S109: and splitting and recombining the loop paths based on the graph neural network. And then returns to step S107.
And (4) splitting and recombining the loop paths by using the same method as the method for initializing the loop path set of the graph to obtain a new loop path set of the graph, and then returning to the step (S107) for iterative computation.
Step S110: and returning to the target path set after the graph optimization.
If the objective function value or the iteration times of the graph optimization meet the second preset condition, the iteration calculation is finished, and the objective function value of the current graph optimization is returned
Set of minimum corresponding graph loop paths
As a set of target paths after graph optimization. The optimized target path set is shown in table 4.
TABLE 4 optimized target Path set
| Serial number | S_paths | S_paths_fp |
| 1 | [A,B,R,D,E,F] | 31.20％ |
| 2 | [A,W,C,T,Y,U,F] | 42.60％ |
Grouping two by two according to the AZ end connection relationship, and the AZ end connection relationship before and after matching optimization is shown in Table 5.
TABLE 5 AZ terminal connection before and after optimization
Step S111: and outputting the rectification scheme.
And outputting the rectification scheme of the target path set. The PTN network element connections as shown in table 6 that need to be added and deleted are output, and finally the target path set as shown in fig. 5 is obtained.
Table 6 PTN network element connections requiring addition or deletion
Step S112: and (6) ending.
The embodiment of the invention optimizes the bandwidth utilization rate of the PTN transmission loop based on the graph neural network, and changes the traditional transmission loop capacity management mode by globally analyzing the service model of the PTN transmission loop network. The embodiment of the invention does not need capacity expansion hardware equipment, and can effectively solve the problem of uneven distribution of PTN capacity utilization rate in the existing network. The embodiment of the invention is applied to the optimization of the utilization rate of the daily PTN transmission loop, can realize global fine capacity expansion, can reduce the capacity expansion cost by 20 percent, and can save the capacity expansion cost by 1000 ten thousand per year. The ratio of the number of the healthy loops is increased from 28.3% to 42.7%, the efficiency is increased by 90% by making a loop out-of-limit card-picking scheme, and the traditional time consumption is reduced to 2.5 hours from 2 days.
The embodiment of the invention obtains the target optimization range of the loop bandwidth utilization rate by obtaining the PTN transmission loop data and preprocessing the PTN transmission loop data; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; iterative optimization is carried out on the graph loop path set based on a graph neural network, the graph loop path set with the minimum graph optimization objective function value is obtained, the problem that the PTN capacity utilization rate of the existing network is not uniformly distributed can be solved, overall fine capacity expansion is achieved, and the cost of manpower and material resources of an enterprise can be reduced.
Fig. 6 is a schematic structural diagram illustrating a PTN transmission loop bandwidth utilization optimizing apparatus according to an embodiment of the present invention. As shown in fig. 6, the PTN transport loop bandwidth utilization optimizing apparatus applied to a server includes: a data acquisition unit 601, a graph generation unit 602, an objective function acquisition unit 603, and an iterative optimization unit 604. Wherein:
the data acquisition unit 601 is configured to acquire PTN transmission loop data, preprocess the PTN transmission loop data, and acquire a target optimization range of a loop bandwidth utilization rate; the graph generating unit 602 is configured to establish a topological structure of a graph for the PTN transmission loop data, and generate a graph loop path set that meets a first preset condition; the objective function obtaining unit 603 is configured to obtain a graph optimization objective function according to the target optimization range of the loop bandwidth utilization; the iterative optimization unit 604 is configured to perform iterative optimization on the graph loop path set based on a graph neural network, and obtain the graph loop path set with the minimum graph optimization objective function value.
In an alternative manner, the data obtaining unit 601 is configured to: taking a district as a unit, and obtaining the average value eta of the bandwidth utilization rate of all loops by applying the following relational expression through a PTN loop flow analysis report form:
adjusting the target optimization range (a, b) of the loop bandwidth utilization ratio to be the average value eta of the loop bandwidth utilization ratio
In an alternative manner, the data obtaining unit 601 is configured to: summing the busy hour average flow rate data of each port of the network element by taking the network element as a unit through a port bandwidth utilization rate report to obtain the busy hour average flow rate of the PTN network element; acquiring a sensitive site identifier through a PTN sensitive site report; construction feasibility constraints are obtained by comprehensively measuring the network element connection distance, the construction cost and natural geological factors.
In an alternative manner, the graph generating unit 602 is configured to: abstracting PTN transmission loop data into a node and edge relation of a graph, and establishing a topological structure of the graph; abstracting a PTN loop into a graph loop path meeting the first preset condition; and adopting a random walk method based on a graph neural network, after selecting a sink node as a path head node each time, diffusing and searching a graph loop path meeting the first preset condition from the random start of the sink node to surrounding nodes until all nodes in the graph are included, and generating the graph loop path set.
In an alternative manner, the objective function obtaining unit 603 is configured to: obtaining a graph optimization target mean from the target optimization range (a, b) of the loop bandwidth utilization
Optimizing a target mean from the graph
Defining graph optimization objective function
Wherein, PjIs a path in the set of graph loop paths,
is path PjJ is a positive integer.
In an alternative approach, the iterative optimization unit 604 is configured to: calculating the graph optimization objective function values for the set of graph loop paths; if the graph optimization objective function value is determined to meet the second preset condition, returning the set of graph loop paths with the minimum graph optimization objective function value; if the graph optimization objective function value is determined not to meet a second preset condition, splitting and recombining paths in the graph loop path set to generate a new graph loop path set; iteratively calculating the graph optimization objective function value of the new set of graph loop paths until the graph optimization objective function value satisfies the second preset condition.
In an alternative manner, the second preset condition includes: the iteration times are greater than the maximum iteration optimization times Max _ times; or the variation value e of the graph optimization objective function value of the current iteration and the last iteration is less than or equal to the minimum variation value threshold emin(ii) a Or the graph optimization objective function value of the current iteration is less than or equal to the minimum value omega.
The embodiment of the invention obtains the target optimization range of the loop bandwidth utilization rate by obtaining the PTN transmission loop data and preprocessing the PTN transmission loop data; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; iterative optimization is carried out on the graph loop path set based on a graph neural network, the graph loop path set with the minimum graph optimization objective function value is obtained, the problem that the PTN capacity utilization rate of the existing network is not uniformly distributed can be solved, overall fine capacity expansion is achieved, and the cost of manpower and material resources of an enterprise can be reduced.
Embodiments of the present invention provide a non-volatile computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction may execute the method for optimizing the bandwidth utilization rate of the PTN transmission loop in any of the above method embodiments.
The executable instructions may be specifically configured to cause the processor to:
PTN transmission loop data are obtained, and the PTN transmission loop data are preprocessed, so that a target optimization range of loop bandwidth utilization rate is obtained;
establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition;
obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate;
and carrying out iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
In an alternative, the executable instructions cause the processor to:
taking a district as a unit, and obtaining the average value eta of the bandwidth utilization rate of all loops by applying the following relational expression through a PTN loop flow analysis report form:
adjusting the target optimization range (a, b) of the loop bandwidth utilization ratio to be the average value eta of the loop bandwidth utilization ratio
In an alternative, the executable instructions cause the processor to:
summing the busy hour average flow rate data of each port of the network element by taking the network element as a unit through a port bandwidth utilization rate report to obtain the busy hour average flow rate of the PTN network element;
acquiring a sensitive site identifier through a PTN sensitive site report;
construction feasibility constraints are obtained by comprehensively measuring the network element connection distance, the construction cost and natural geological factors.
In an alternative, the executable instructions cause the processor to:
abstracting PTN transmission loop data into a node and edge relation of a graph, and establishing a topological structure of the graph;
abstracting a PTN loop into a graph loop path meeting the first preset condition;
and adopting a random walk method based on a graph neural network, after selecting a sink node as a path head node each time, diffusing and searching a graph loop path meeting the first preset condition from the random start of the sink node to surrounding nodes until all nodes in the graph are included, and generating the graph loop path set.
In an alternative, the executable instructions cause the processor to:
obtaining a graph optimization target mean from the target optimization range (a, b) of the loop bandwidth utilization
Optimizing a target mean from the graph
Defining graph optimization objective function
Wherein, PjIs the set of loop paths of the graphThe path in the convergence is the path in the convergence,
is path PjJ is a positive integer.
In an alternative, the executable instructions cause the processor to:
calculating the graph optimization objective function values for the set of graph loop paths;
if the graph optimization objective function value is determined to meet the second preset condition, returning the set of graph loop paths with the minimum graph optimization objective function value;
if the graph optimization objective function value is determined not to meet a second preset condition, splitting and recombining paths in the graph loop path set to generate a new graph loop path set;
iteratively calculating the graph optimization objective function value of the new set of graph loop paths until the graph optimization objective function value satisfies the second preset condition.
In an alternative manner, the second preset condition includes:
the iteration times are greater than the maximum iteration optimization times Max _ times; or
The variation value e of the graph optimization objective function value of the current iteration and the last iteration is less than or equal to the minimum variation value threshold emin(ii) a Or
The graph optimization objective function value of the current iteration is less than or equal to a minimum value omega.
The embodiment of the invention obtains the target optimization range of the loop bandwidth utilization rate by obtaining the PTN transmission loop data and preprocessing the PTN transmission loop data; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; iterative optimization is carried out on the graph loop path set based on a graph neural network, the graph loop path set with the minimum graph optimization objective function value is obtained, the problem that the PTN capacity utilization rate of the existing network is not uniformly distributed can be solved, overall fine capacity expansion is achieved, and the cost of manpower and material resources of an enterprise can be reduced.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform a method for optimizing a bandwidth utilization of a PTN transmission loop in any of the above-described method embodiments.
The executable instructions may be specifically configured to cause the processor to:
PTN transmission loop data are obtained, and the PTN transmission loop data are preprocessed, so that a target optimization range of loop bandwidth utilization rate is obtained;
establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition;
obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate;
and carrying out iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
In an alternative, the executable instructions cause the processor to:
taking a district as a unit, and obtaining the average value eta of the bandwidth utilization rate of all loops by applying the following relational expression through a PTN loop flow analysis report form:
adjusting the target optimization range (a, b) of the loop bandwidth utilization ratio to be the average value eta of the loop bandwidth utilization ratio
In an alternative, the executable instructions cause the processor to:
summing the busy hour average flow rate data of each port of the network element by taking the network element as a unit through a port bandwidth utilization rate report to obtain the busy hour average flow rate of the PTN network element;
acquiring a sensitive site identifier through a PTN sensitive site report;
construction feasibility constraints are obtained by comprehensively measuring the network element connection distance, the construction cost and natural geological factors.
In an alternative, the executable instructions cause the processor to:
abstracting PTN transmission loop data into a node and edge relation of a graph, and establishing a topological structure of the graph;
abstracting a PTN loop into a graph loop path meeting the first preset condition;
and adopting a random walk method based on a graph neural network, after selecting a sink node as a path head node each time, diffusing and searching a graph loop path meeting the first preset condition from the random start of the sink node to surrounding nodes until all nodes in the graph are included, and generating the graph loop path set.
In an alternative, the executable instructions cause the processor to:
obtaining a graph optimization target mean from the target optimization range (a, b) of the loop bandwidth utilization
Optimizing a target mean from the graph
Defining graph optimization objective function
Wherein, PjIs in the set of loop paths of the graphThe path of the beam is a path of the beam,
is path PjJ is a positive integer.
In an alternative, the executable instructions cause the processor to:
calculating the graph optimization objective function values for the set of graph loop paths;
if the graph optimization objective function value is determined to meet the second preset condition, returning the set of graph loop paths with the minimum graph optimization objective function value;
if the graph optimization objective function value is determined not to meet a second preset condition, splitting and recombining paths in the graph loop path set to generate a new graph loop path set;
iteratively calculating the graph optimization objective function value of the new set of graph loop paths until the graph optimization objective function value satisfies the second preset condition.
In an alternative manner, the second preset condition includes:
the iteration times are greater than the maximum iteration optimization times Max _ times; or
The variation value e of the graph optimization objective function value of the current iteration and the last iteration is less than or equal to the minimum variation value threshold emin(ii) a Or
The graph optimization objective function value of the current iteration is less than or equal to a minimum value omega.
The embodiment of the invention obtains the target optimization range of the loop bandwidth utilization rate by obtaining the PTN transmission loop data and preprocessing the PTN transmission loop data; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; iterative optimization is carried out on the graph loop path set based on a graph neural network, the graph loop path set with the minimum graph optimization objective function value is obtained, the problem that the PTN capacity utilization rate of the existing network is not uniformly distributed can be solved, overall fine capacity expansion is achieved, and the cost of manpower and material resources of an enterprise can be reduced.
Fig. 7 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the device.
As shown in fig. 7, the computing device may include: a processor (processor)702, a Communications Interface 704, a memory 706, and a communication bus 708.
Wherein: the processor 702, communication interface 704, and memory 706 communicate with each other via a communication bus 708. A communication interface 704 for communicating with network elements of other devices, such as clients or other servers. The processor 702 is configured to execute the program 710, and may specifically execute relevant steps in the above-described PTN transmission loop bandwidth utilization optimization method embodiment.
In particular, the program 710 may include program code that includes computer operating instructions.
The processor 702 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention. The one or each processor included in the device may be the same type of processor, such as one or each CPU; or may be different types of processors such as one or each CPU and one or each ASIC.
The memory 706 stores a program 710. The memory 706 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 710 may specifically be used to cause the processor 702 to perform the following operations:
PTN transmission loop data are obtained, and the PTN transmission loop data are preprocessed, so that a target optimization range of loop bandwidth utilization rate is obtained;
establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition;
obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate;
and carrying out iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
In an alternative, the program 710 causes the processor to:
taking a district as a unit, and obtaining the average value eta of the bandwidth utilization rate of all loops by applying the following relational expression through a PTN loop flow analysis report form:
adjusting the target optimization range (a, b) of the loop bandwidth utilization ratio to be the average value eta of the loop bandwidth utilization ratio
In an alternative, the program 710 causes the processor to:
summing the busy hour average flow rate data of each port of the network element by taking the network element as a unit through a port bandwidth utilization rate report to obtain the busy hour average flow rate of the PTN network element;
acquiring a sensitive site identifier through a PTN sensitive site report;
construction feasibility constraints are obtained by comprehensively measuring the network element connection distance, the construction cost and natural geological factors.
In an alternative, the program 710 causes the processor to:
abstracting PTN transmission loop data into a node and edge relation of a graph, and establishing a topological structure of the graph;
abstracting a PTN loop into a graph loop path meeting the first preset condition;
and adopting a random walk method based on a graph neural network, after selecting a sink node as a path head node each time, diffusing and searching a graph loop path meeting the first preset condition from the random start of the sink node to surrounding nodes until all nodes in the graph are included, and generating the graph loop path set.
In an alternative, the program 710 causes the processor to:
obtaining a graph optimization target mean from the target optimization range (a, b) of the loop bandwidth utilization
Optimizing a target mean from the graph
Defining graph optimization objective function
Wherein, PjIs a path in the set of graph loop paths,
is path PjJ is a positive integer.
In an alternative, the program 710 causes the processor to:
calculating the graph optimization objective function values for the set of graph loop paths;
if the graph optimization objective function value is determined to meet the second preset condition, returning the set of graph loop paths with the minimum graph optimization objective function value;
if the graph optimization objective function value is determined not to meet a second preset condition, splitting and recombining paths in the graph loop path set to generate a new graph loop path set;
iteratively calculating the graph optimization objective function value of the new set of graph loop paths until the graph optimization objective function value satisfies the second preset condition.
In an alternative manner, the second preset condition includes:
the iteration times are greater than the maximum iteration optimization times Max _ times; or
The variation value e of the graph optimization objective function value of the current iteration and the last iteration is less than or equal to the minimum variation value threshold emin(ii) a Or
The graph optimization objective function value of the current iteration is less than or equal to a minimum value omega.
The embodiment of the invention obtains the target optimization range of the loop bandwidth utilization rate by obtaining the PTN transmission loop data and preprocessing the PTN transmission loop data; establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition; obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate; iterative optimization is carried out on the graph loop path set based on a graph neural network, the graph loop path set with the minimum graph optimization objective function value is obtained, the problem that the PTN capacity utilization rate of the existing network is not uniformly distributed can be solved, overall fine capacity expansion is achieved, and the cost of manpower and material resources of an enterprise can be reduced.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A method for optimizing bandwidth utilization of a PTN transmission loop, the method comprising:
PTN transmission loop data are obtained, and the PTN transmission loop data are preprocessed, so that a target optimization range of loop bandwidth utilization rate is obtained;
establishing a topological structure of a graph for the PTN transmission loop data, and generating a graph loop path set meeting a first preset condition;
obtaining a graph optimization objective function according to the objective optimization range of the loop bandwidth utilization rate;
and carrying out iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
2. The method of claim 1, wherein preprocessing the PTN transmission loop data to obtain a target optimization range of loop bandwidth utilization comprises:
taking a district as a unit, and obtaining the average value eta of the bandwidth utilization rate of all loops by applying the following relational expression through a PTN loop flow analysis report form:
adjusting the target optimization range (a, b) of the loop bandwidth utilization ratio to be the average value eta of the loop bandwidth utilization ratio
3. The method of claim 1, wherein the preprocessing the PTN transmission loop data further comprises:
summing the busy hour average flow rate data of each port of the network element by taking the network element as a unit through a port bandwidth utilization rate report to obtain the busy hour average flow rate of the PTN network element;
acquiring a sensitive site identifier through a PTN sensitive site report;
construction feasibility constraints are obtained by comprehensively measuring the network element connection distance, the construction cost and natural geological factors.
4. The method according to claim 1, wherein the mapping the PTN transmission loop data into a topology structure, and generating a set of graph loop paths satisfying a first preset condition comprises:
abstracting PTN transmission loop data into a node and edge relation of a graph, and establishing a topological structure of the graph;
abstracting a PTN loop into a graph loop path meeting the first preset condition;
and adopting a random walk method based on a graph neural network, after selecting a sink node as a path head node each time, diffusing and searching a graph loop path meeting the first preset condition from the random start of the sink node to surrounding nodes until all nodes in the graph are included, and generating the graph loop path set.
5. The method of claim 1, wherein obtaining a graph optimization objective function according to the target optimization range of the loop bandwidth utilization comprises:
obtaining a graph optimization target mean from the target optimization range (a, b) of the loop bandwidth utilization
Optimizing a target mean from the graph
Defining graph optimization objective function
Wherein, PjIs a path in the set of graph loop paths,
is path PjJ is a positive integer.
6. The method of claim 1, wherein iteratively optimizing the set of graph loop paths based on a graph neural network to obtain the set of graph loop paths with the smallest graph optimization objective function value comprises:
calculating the graph optimization objective function values for the set of graph loop paths;
if the graph optimization objective function value is determined to meet the second preset condition, returning the set of graph loop paths with the minimum graph optimization objective function value;
if the graph optimization objective function value is determined not to meet a second preset condition, splitting and recombining paths in the graph loop path set to generate a new graph loop path set;
iteratively calculating the graph optimization objective function value of the new set of graph loop paths until the graph optimization objective function value satisfies the second preset condition.
7. The method according to claim 6, wherein the second preset condition comprises:
the iteration times are greater than the maximum iteration optimization times Max _ times; or
The variation value e of the graph optimization objective function value of the current iteration and the last iteration is less than or equal to the minimum variation value threshold emin(ii) a Or
The graph optimization objective function value of the current iteration is less than or equal to a minimum value omega.
8. An apparatus for optimizing bandwidth utilization of a PTN transmission loop, the apparatus comprising:
the data acquisition unit is used for acquiring PTN transmission loop data, preprocessing the PTN transmission loop data and acquiring a target optimization range of loop bandwidth utilization rate;
the graph generating unit is used for establishing a topological structure of a graph by the PTN transmission loop data and generating a graph loop path set meeting a first preset condition;
the target function obtaining unit is used for obtaining a graph optimization target function according to the target optimization range of the loop bandwidth utilization rate;
and the iterative optimization unit is used for performing iterative optimization on the graph loop path set based on a graph neural network to obtain the graph loop path set with the minimum graph optimization objective function value.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the steps of the PTN transport loop bandwidth utilization optimization method according to any one of claims 1 to 7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform the steps of the PTN transport loop bandwidth utilization optimization method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010245438.1A CN113473266B (en) | 2020-03-31 | 2020-03-31 | Method and device for optimizing bandwidth utilization rate of PTN transmission loop and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010245438.1A CN113473266B (en) | 2020-03-31 | 2020-03-31 | Method and device for optimizing bandwidth utilization rate of PTN transmission loop and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113473266A true CN113473266A (en) | 2021-10-01 |
| CN113473266B CN113473266B (en) | 2023-04-11 |
Family
ID=77865547
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010245438.1A Active CN113473266B (en) | 2020-03-31 | 2020-03-31 | Method and device for optimizing bandwidth utilization rate of PTN transmission loop and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113473266B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101212348A (en) * | 2006-12-31 | 2008-07-02 | 中兴通讯股份有限公司 | Resilient packet ring based graphical display method for service topology |
| CN107241273A (en) * | 2017-06-23 | 2017-10-10 | 江苏省邮电规划设计院有限责任公司 | A kind of communications ring network structure method to set up based on genetic algorithm |
| CN110024328A (en) * | 2016-10-30 | 2019-07-16 | 张惠明 | A kind of communication network with control planar network |
-
2020
- 2020-03-31 CN CN202010245438.1A patent/CN113473266B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101212348A (en) * | 2006-12-31 | 2008-07-02 | 中兴通讯股份有限公司 | Resilient packet ring based graphical display method for service topology |
| CN110024328A (en) * | 2016-10-30 | 2019-07-16 | 张惠明 | A kind of communication network with control planar network |
| CN107241273A (en) * | 2017-06-23 | 2017-10-10 | 江苏省邮电规划设计院有限责任公司 | A kind of communications ring network structure method to set up based on genetic algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 王昌廷: "《接入层PTN网络结构优化探讨》", 《电子世界》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113473266B (en) | 2023-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109104464B (en) | Distributed data updating method for collaborative storage in edge computing environment | |
| CN112738820A (en) | Dynamic deployment method and device of service function chain and computer equipment | |
| CN111538570B (en) | Energy-saving and QoS guarantee-oriented VNF deployment method and device | |
| CN109639575A (en) | Route planning method based on link congestion coefficient | |
| CN102281290A (en) | Emulation system and method for a PaaS (Platform-as-a-service) cloud platform | |
| CN113190939B (en) | Large sparse complex network topology analysis and simplification method based on polygon coefficient | |
| CN110968426A (en) | Edge cloud collaborative k-means clustering model optimization method based on online learning | |
| CN105677447A (en) | Clustering-based delay bandwidth minimization virtual machine deployment method in distributed cloud | |
| CN109921939A (en) | The choosing method and system of key node in a kind of communication network | |
| CN109343945A (en) | A kind of multitask dynamic allocation method based on contract net algorithm | |
| Guo et al. | Particle swarm optimization based multi-domain virtual network embedding | |
| Zheng et al. | Minimizing the latency of embedding dependence-aware sfcs into mec network via graph theory | |
| CN113473266B (en) | Method and device for optimizing bandwidth utilization rate of PTN transmission loop and computing equipment | |
| Zhao et al. | Virtual network embedding based on node connectivity awareness and path integration evaluation | |
| CN114330184B (en) | Multi-level grouping method and device | |
| CN109889573A (en) | Based on the Replica placement method of NGSA multiple target in mixed cloud | |
| Bujnowski et al. | The possibility of equalising the transmission properties of networks described by chordal rings | |
| CN107911245A (en) | Virtual network mapping model and algorithm in a kind of core elastic optical network | |
| CN114599043A (en) | Air-space-ground integrated network resource allocation method based on deep reinforcement learning | |
| Guan et al. | Multidimensional Resource Fragmentation-Aware Virtual Network Embedding for IoT Applications in MEC Networks | |
| CN116683981B (en) | Low-orbit satellite path planning method based on multidimensional time-varying resource diagram | |
| CN102625198B (en) | Intelligent light resource configuration method and system | |
| CN112446485A (en) | Neural network collaborative training method and device and related products | |
| Appleby | Estimating the cost of a telecommunications network using the fractal structure of the human population distribution | |
| Shahin | Using heavy clique base coarsening to enhance virtual network embedding |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |