CN117376081A - Network maintenance method based on deterministic network - Google Patents
Network maintenance method based on deterministic network Download PDFInfo
- Publication number
- CN117376081A CN117376081A CN202311530243.1A CN202311530243A CN117376081A CN 117376081 A CN117376081 A CN 117376081A CN 202311530243 A CN202311530243 A CN 202311530243A CN 117376081 A CN117376081 A CN 117376081A
- Authority
- CN
- China
- Prior art keywords
- service
- server
- stable
- server group
- group
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000012423 maintenance Methods 0.000 title claims abstract description 28
- 238000013508 migration Methods 0.000 claims abstract description 93
- 230000005012 migration Effects 0.000 claims abstract description 93
- 238000004364 calculation method Methods 0.000 claims abstract description 61
- 230000002452 interceptive effect Effects 0.000 claims abstract description 59
- 238000012216 screening Methods 0.000 claims abstract description 12
- 238000009826 distribution Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 44
- 230000008569 process Effects 0.000 claims description 37
- 230000002776 aggregation Effects 0.000 claims description 33
- 238000004220 aggregation Methods 0.000 claims description 33
- 239000012634 fragment Substances 0.000 claims description 30
- 238000003860 storage Methods 0.000 claims description 27
- 230000005855 radiation Effects 0.000 claims description 25
- 230000003993 interaction Effects 0.000 claims description 13
- 238000004806 packaging method and process Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
- H04L67/1046—Joining mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
- H04L67/1048—Departure or maintenance mechanisms
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a network maintenance method based on a deterministic network, and relates to the technical field of network maintenance. The method specifically comprises the following steps: setting a deterministic network, and screening a stable server according to the deterministic network; according to the distribution condition of the stable server, obtaining a stable server group, screening the services authorized by the stable server group if the stable server group has the condition of insufficient calculation power, marking the services wasting the calculation power of the stable server as stream play services, and carrying out migration treatment on the stream play services; when the streaming service is migrated, if the streaming service is detected at the port of the stable server, the streaming service is judged to be the interactive service, and corresponding adjustment measures are implemented according to the interactive stage of the interactive service.
Description
Technical Field
The invention relates to the technical field of network maintenance, in particular to a network maintenance method based on a deterministic network.
Background
Deterministic networks are relative to traditional "best effort" networks, the most typical of which is the internet. The internet can meet many life applications, such as browsing web pages, sending and receiving mail, watching web videos, etc., which have low requirements on certainty of transmission. The deterministic network is a novel network technology, has the advantages of large bandwidth, low delay, low jitter, high reliability and the like, and can effectively solve the problems of congestion, delay, jitter and other pain points in the traditional network data transmission.
However, as the data to be processed increases, huge data volume has a non-negligible effect on the efficient operation of the deterministic network, and how to maintain the normal operation of the deterministic network, so as to avoid the situation that the server supporting the deterministic network generates insufficient computational power resources is a difficulty in the prior art.
Disclosure of Invention
In view of the above drawbacks of the prior art, the present invention provides a network maintenance method based on deterministic network, which solves the technical problems set forth in the above background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
a deterministic network-based network maintenance method, comprising the steps of:
step 1: setting a deterministic network, screening servers conforming to the transacted deterministic network service according to the deterministic network, and marking the servers conforming to the transacted deterministic network service as stable servers;
step 2: obtaining a stable server group according to the distribution condition of the stable servers, wherein the stable server group consists of a core machine group, a radiation machine group and an edge machine group, and carrying out grading treatment on the stable server group according to the calculation power of the stable server group;
Step 3: the service authorized by the deterministic network is classified, and the stable server group corresponding to the class is matched according to the class of the service, so that the service can be efficiently and stably processed; if the stable server group has the condition of insufficient calculation power, screening the services managed by the stable server group, marking the services wasting the calculation power of the stable server as stream play services, and performing migration processing on the stream play services so as to ensure that the stable server can operate efficiently and stably;
step 4: when migration processing is carried out on the streaming service, if the streaming service is detected at the port of the stable server, the streaming service is judged to be an interactive service, and the interactive service is the service under processing; if the interactive service exists, corresponding adjustment measures are implemented according to the interactive stage where the interactive service is located.
Still further, the process of setting up a deterministic network includes:
training the demand data and the capacity data through a convolutional neural network, a depth residual error network and a transducer model to obtain a deterministic network generation algorithm; the demand data is input and acquired by a user; the capability data is the performance data of the server;
Setting a network service period; the user carries out network deployment according to the deterministic network generated by the deterministic network generation algorithm, generates network quality parameters through a network use period, judges whether the network quality of the deterministic network is qualified or not through the network quality parameters, can continue to use if the network quality is qualified, and can not continue to use if the network quality is unqualified.
Further, the process of obtaining the stable server is as follows:
establishing a space rectangular coordinate system;
obtaining the geographic position of a stable server;
acquiring the geometric position of a stable server according to the geographic position;
according to the geometric positions of the stable servers, obtaining the x-y distance and the x-z distance between the stable servers, and generating an x-y set and an x-z set;
acquiring an x-y aggregation coordinate set of the stable server according to the x-y aggregation coordinate set through the x range overlap ratio, and acquiring an x-z aggregation coordinate set of the stable server according to the x-z aggregation coordinate set;
judging whether a stable server group can be formed according to the x-y aggregation coordinate set and the x-z aggregation coordinate set of the stable server through the x range matching degree; if the stable server group can be formed, combining the x-y aggregation coordinate set and the x-z aggregation coordinate set to generate the stable server group; if the stable server group cannot be formed, no operation is needed;
And generating a core cluster, a radiation cluster and an edge cluster according to the geometric distance and the magnitude order among the stable server clusters.
Further, the process of grading the stable server group according to the calculation force is as follows:
acquiring bit rate, concurrency, throughput, time delay and channel utilization rate of a stable server, and obtaining calculation power of the stable server through a calculation power formula;
setting a calculation force level threshold, and judging the level class of the stable server according to the calculation force level threshold and the calculation force; the rank categories include: the system comprises a first-level computing power server, a second-level computing power server, a third-level computing power server and a fourth-level computing power server.
Further, the service grading processing process comprises the following steps:
the stable server group is internally provided with a service storage unit for storing specific information of services, wherein the specific information comprises a home code, a service model, service content, service volume and service grade;
calculating the business volume, submitting frequency, business weight and attribution weight of the business through a business grading formula, obtaining business grade weight, and grading the business according to the business grade weight;
the service weight is assigned according to the service model, the service volume is the service volume in the service storage unit, the submitting frequency is obtained through calculation of the service storage unit according to a frequency formula, and the attribution weight is assigned according to the attribution code;
Setting a service grade threshold, and judging the grade category of the service according to the service grade threshold and the service grade weight; the rank categories include: primary, secondary, tertiary and quaternary services.
Further, the matching process of the stable server group corresponding to the service level matching level is as follows:
the first-level business is processed by a first-level computing power server; the second-level business is processed by a second-level computing power server; the third-level business is processed by a third-level computing power server; the fourth-level business is processed by a fourth-level computing power server;
if the computing power server corresponding to the current service level does not have idle resources, the superior computing power server is applied to process the service; if the superior computing power server does not have the idle resources, the superior computing power server of the superior computing power server is applied to process the service until the highest computing power server is requested;
the upper-level computing power server is a server with the computing power level higher than that of the current computing power server;
the highest power calculating server is the highest-level power calculating server;
if the highest-level computing power server still has no idle resources, generating first-level early warning information to inform a user of insufficient computing power, automatically screening services managed by the stable server group, marking the service wasting the resources as a streaming service, and performing migration processing on the streaming service.
Further, the identification process of the playing service is as follows:
setting a release threshold;
acquiring the streaming weight of the service according to the streaming weight formula;
if the traffic stream weight is greater than the stream threshold, marking the traffic as stream traffic and marking the attribution code and the traffic model of the traffic as stream index;
if the traffic flow weight is less than or equal to the flow threshold, no operation is needed for the traffic.
Further, the migration process comprises the following steps:
generating a streaming request according to the streaming index, and submitting the streaming request to a service storage unit;
the service storage unit inquires the service according to the stream index and generates a stream service set;
generating a migration application according to the streaming service set, submitting the migration application to a radiation machine group of the stable server group, generating migration permission information according to an MAC address of the radiation machine group if the radiation machine group agrees to migrate, sending the migration permission information to the stable server group, and returning migration refusal information if the radiation machine group disagrees to migrate;
if the stable server group receives migration permission information, marking a radiation machine group to which the MAC address belongs as a target machine group according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target machine group;
If the replies received by the stable server group are refusal migration information, a migration application is sent to a core cluster of the stable server group; if the core machine group agrees to migrate, the core machine group generates migration permission information according to the self MAC address and sends the migration permission information to the stable server group, and if the core machine group disagrees to migrate, the core machine group returns migration refusal information;
if the stable server group receives migration permission information, marking a core cluster to which the MAC address belongs as a target cluster according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target cluster;
if the replies received by the stable server group are refusal migration information, sending a migration application to the edge cluster with the closest geometric distance; if the edge cluster agrees to migrate, the edge cluster generates migration permission information according to the self MAC address and sends the migration permission information to the stable server cluster, and if the edge cluster does not agree to migrate, the edge cluster returns migration refusal information;
if the stable server group receives migration permission information, marking an edge cluster to which the MAC address belongs as a target cluster according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target cluster;
If the stable server group receives the refused migration information, generating second-level early warning information, informing the user that the computing power is seriously insufficient, and taking corresponding measures by the user.
Still further, the process of implementing the corresponding adjustment measure according to the interaction phase includes:
the interaction stage of the interaction service comprises a handshake stage, a processing stage and a waving stage;
marking a stable server group for transmitting the streaming service set as a source server group, and marking a stable server group for receiving the streaming service set as a target server group;
if the interactive service is in the handshake phase, sending refusal connection information to a stable server submitting the interactive service, generating connection change information according to the IP address of the target server group, and sending the connection change information to the stable server submitting the interactive service; meanwhile, the source server group packages and sends the local data of the interactive service to the target server group, wherein the local data is the service specific information of the home code, the service model and the interactive service in the service storage unit; the source server group packages and sends the local data to the target server group, the target server group sends a receiving success signal to the source server group after receiving the receiving success signal, and the source server group deletes the local data after receiving the receiving success signal;
If the interactive service is in the processing stage, carrying out 'side processing, side migration and side verification'; the method comprises the steps that an origin server group processes interactive services according to a normal processing flow, meanwhile, the origin server group cuts local data of the interactive services to obtain data fragments, copies the data fragments to generate copy fragments, packages the copy fragments to be sent to a target server group, copies the copy fragments after receiving the copy fragments to generate check data, packages the check data to the origin server group, compares the check data with the data fragments after receiving the check data, cuts, copies, packages and sends the next time if the comparison result is the same, sends error signals to the target server group to delete the data fragments if the comparison result is different, and repacks and sends the data fragments; after the migration processing of the interactive service is finished, the target server group splices the received plurality of copy fragments according to the receiving sequence to generate copy data, copies the copy data to generate check data, sends the check data to the source server group, compares the check data with the local data after the source server group receives the check data, sends a migration success signal to the target server group if the comparison result is the same, and deletes the local data; if the comparison results are different, the local data are packaged and sent to a target server group, after the target server group receives the signals successfully, the target server group sends the signals successfully received to a source server group, and after the source server group receives the signals successfully received, the local data are deleted;
If the interactive service is in the waving stage, waiting for the waving of the interactive service to finish, namely disconnecting; after the waving is finished, the source server group packages and sends the local data of the interactive service to the target server group, the target server group sends a successful receiving signal to the source server group after receiving the successful receiving signal, and the source server group deletes the local data after receiving the successful receiving signal.
Compared with the known public technology, the technical scheme provided by the invention has the following beneficial effects:
1. according to the invention, through screening the service of the server, when the situation of insufficient computing power resources occurs in the server, the service wasting the computing power resources of the server is marked as the stream service, and the stream service is subjected to migration processing, so that the dynamic adjustment of the service of the server is achieved, the server can flexibly control the computing power resources, the computing power resources of the server are effectively utilized, and meanwhile, the situation of shortage of the computing power resources of the server is relieved.
2. When the invention carries out migration processing on the stream playing service, the port of the server is detected to check whether the stream playing service is in process of being transacted, if the stream playing service is in process of being transacted, the service is marked as an interactive service, and corresponding adjustment measures are implemented according to the interactive stage where the interactive service is located, so that the integrity and the correctness of the migrated stream playing service are ensured, and the tampering behavior of data in the process of being transacted and transferred is avoided.
3. The invention prevents the tampering behavior of the data in the process of handling and transferring the data by checking for many times in time, and simultaneously carries out the integrity check of the transferred data and the data before transferring after the data transfer is finished, and if errors exist, the data is retransmitted, thereby greatly avoiding the situation of transmitting error data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
Fig. 1 is a flow chart of a deterministic network-based network maintenance method.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is further described below with reference to examples.
Example 1
The network maintenance method based on deterministic network in this embodiment, as shown in fig. 1, includes the following steps:
step 1: setting a deterministic network, screening servers conforming to the transacted deterministic network service according to the deterministic network, and marking the servers conforming to the transacted deterministic network service as stable servers;
step 2: obtaining a stable server group according to the distribution condition of the stable servers, wherein the stable server group consists of a core machine group, a radiation machine group and an edge machine group, and carrying out grading treatment on the stable server group according to the calculation power of the stable server group;
step 3: the service authorized by the deterministic network is classified, and the stable server group corresponding to the class is matched according to the class of the service, so that the service can be efficiently and stably processed; if the stable server group has the condition of insufficient calculation power, screening the services managed by the stable server group, marking the services wasting the calculation power of the stable server as stream play services, and performing migration processing on the stream play services so as to ensure that the stable server can operate efficiently and stably;
Step 4: when migration processing is carried out on the streaming service, if the streaming service is detected at the port of the stable server, the streaming service is judged to be an interactive service, and the interactive service is the service under processing; if the interactive service exists, implementing corresponding adjustment measures according to the interactive stage where the interactive service is located;
example 2
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the process of setting the deterministic network in the step 1 comprises the following steps:
training the demand data D and the capacity data A through a convolutional neural network, a depth residual error network and a transducer model to obtain a deterministic network generation algorithm;
the demand data D is obtained by user input:
wherein E= [ E 1 E 2 E 3 …]，I＝[I 1 I 2 I 3 …]，S＝[S 1 S 2 S 3 …]，R＝[R 1 R 2 R 3 …]；
E is environmental information, I is industry information, S is business information, and R is demand information;
the environment information is context related information, including policy information, economic development situation information, population change situation information, seasonal climate information, holiday information, geographic position information and social activity information;
The industry information is specific information of the industry, for example, specific information of the industry field comprises industrial production information, equipment material purchasing information, logistics information, supply chain information, product information and after-sale information;
the service information is specific information of the service, for example, the specific information of the video acquisition service comprises video code rate, video path number, video forwarding direction and video storage period;
the requirement information is the network requirement of a user for transacting business, and comprises a bandwidth requirement, a time delay requirement and a safety requirement;
the capability data A is the performance data of the server:
wherein C= [ C 1 C 2 C 3 …]，N＝[N 1 N 2 N 3 …]，St＝[St 1 St 2 St 3 …]，Se＝[Se 1 Se 2 Se 3 …]；
C is computing capacity, N is network capacity, st is storage capacity, se is security capacity;
the computing power capability is computing power related information of the server and comprises bare metal information, virtual machine information, container information, vCPU information and vGPU information;
the network capability is the network transmission related information of the server, and comprises bandwidth, jitter, time delay and packet loss;
the storage capacity is the storage information of the server and comprises storage capacity, a backup mode and a storage protocol;
the security capability is the security defense information of the server, and comprises FW, IPS, IDS and WAF;
Setting a network service period W;
the user carries out network deployment according to the deterministic network generated by the deterministic network generation algorithm, generates a network quality parameter tau through the use of a period W, judges whether the network quality of the deterministic network is qualified or not through the network quality parameter tau, can continue to use if the network quality is qualified, and can not continue to use if the network quality is unqualified;
wherein Ap is a subjective evaluation value of 0<Ap≤1；Ap max The subjective evaluation value is 1; t (T) con For propagation delay, T, of server dt Processing time delay of the server;
setting a qualified threshold k;
if tau is greater than or equal to k, judging the network quality of the deterministic network to be qualified, and carrying out subsequent service interaction and processing; if tau is smaller than k, judging that the network quality of the deterministic network is unqualified, and not carrying out subsequent service interaction and processing, and removing the network deployment of the deterministic network;
example 3
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the process of acquiring the stable server in the step 1 is as follows:
obtaining subjective evaluation values of users, and generating an evaluation value set Aps;
Acquiring propagation delay T of server con And processing delay T dt Obtaining a time delay product T al ＝T con ×T dt ；
Setting a function manynum (X), wherein X is a natural number set and is used for obtaining the mode of the natural number set X;
if the time delay is multiplied by T al Less thanJudging that the server is a stable server, and handling the service of the deterministic network; if the time delay is multiplied by T al Greater than or equal to->Judging that the server is an unstable server and cannot handle the service of the deterministic network;
example 4
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the process of obtaining the stable server group in the step 2 is as follows:
establishing a space rectangular coordinate system;
obtaining the geographic position of a stable server;
acquiring the geometric position of a stable server according to the geographic position;
according to the geometric positions of the stable servers, obtaining the x-y distance and the x-z distance between the stable servers, and generating an x-y set and an x-z set;
acquiring an x-y aggregation coordinate set of the stable server according to the x-y aggregation coordinate set through the x range overlap ratio, and acquiring an x-z aggregation coordinate set of the stable server according to the x-z aggregation coordinate set;
Judging whether a stable server group can be formed according to the x-y aggregation coordinate set and the x-z aggregation coordinate set of the stable server through the x range matching degree; if the stable server group can be formed, combining the x-y aggregation coordinate set and the x-z aggregation coordinate set to generate the stable server group; if the stable server group cannot be formed, no operation is needed;
generating a core cluster, a radiation cluster and an edge cluster according to the geometric distance and the magnitude order among the stable server clusters;
it is assumed that there are several stable servers whose geometrical positions are (x 1 ，y 1 ，z 1 )、(x 2 ，y 2 ，z 2 )、……、(x n ，y n ，z n ) Wherein n is a positive integer;
through the formula of the distance between two points in the planeRespectively obtaining x-y distances L between stable servers x-y And x-z distance L x-z Generating an x-y set H L(x-y) And x-z set H L(x-z) ；
The process for acquiring the x-y aggregation coordinate set of the stable server is as follows:
the geometric position of one stable server is arbitrarily selected as a core point, the geometric positions of other stable servers except the core point are marked as related points, and the geometric positions are collected by an x-y set H L(x-y) Acquiring x-y distance L between core point and associated point x-y ；
Step y1: setting an association threshold GL;
step y2: if the x-y distance L between the core point and the associated point x-y If the correlation point is smaller than or equal to the correlation threshold GL, marking the correlation point as a near correlation point;
step y3: acquiring the x-y distance L 'between the near correlation point and the correlation point' x-y If the x-y distance L' x-y If the correlation point is smaller than or equal to the correlation threshold GL, marking the correlation point as a near correlation point;
repeatedly executing the step y3 until a new near association point cannot be generated;
setting an order threshold GS;
if the number of near-association points of the core point is larger than or equal to the magnitude threshold GS, generating an x-y aggregate coordinate set of the core point according to the core point and the near-association points;
generating an x range of the x-y aggregate coordinate set of the core point according to the maximum value and the minimum value of the x values in the x-y aggregate coordinate set of the core point;
step c1: setting the overlap ratio CH of the x range x ；
Step c2: respectively acquiring x ranges of all the x-y aggregation coordinate sets for comparison, if a superposition part exists between the x range of the x-y aggregation coordinate set of the core point A and the x range of the x-y aggregation coordinate set of the core point B, and the occupation degree of the superposition part in the x range of the core point A and the x range of the core point B is larger than or equal to the x range superposition degree CH x Combining the x-y aggregate coordinate set of the core point A and the x-y aggregate coordinate set of the core point B to generate a new x-y aggregate coordinate set of the core point AB, and generating an x range of the core point AB according to the x range of the core point A and the x range of the core point B;
I.e. the x-range of the x-y aggregate coordinate set of core point a is [2,6 ]]The x-range of the x-y aggregate coordinate set of core point B is [3,6]The overlapping portion is [3,6 ]]The method comprises the steps of carrying out a first treatment on the surface of the Overlap portions [3,6]The ratio in the x range of the core point A is 75%, the overlapping parts [3,6]The ratio of the core point B to the x range is 100%, if 75% and 100% are greater than or equal to the x range overlap CH x Then the x-y aggregate coordinate set of the core point A { (x) a1 ，y a1 )，(x a2 ，y a2 )，……，(x an ，y an ) X-y aggregate coordinate set of core point B { (x) b1 ，y b1 )，(x b2 ，y b2 )，……，(x bn ，y bn ) Merging to generate a new x-y aggregate coordinate set of core points AB { (x) a1 ，y a1 )，(x a2 ，y a2 )，……，(x an ，y an )，(x b1 ，y b1 )，(x b2 ，y b2 )，……，(x bn ，y bn ) X-range of x-y aggregate coordinate set of core point AB is [2,6 ]]；
Repeating the step c2 until a new x-y aggregate coordinate set cannot be generated by merging;
similarly, an x-z aggregation coordinate set of the stable server can be obtained;
setting the matching degree PP of an x range x ；
Respectively acquiring the X range of the X-Y aggregation coordinate set and the X range of the X-z aggregation coordinate set of each stable server, if the matching degree of the X range of the X-Y aggregation coordinate set of the core point X and the X range of the X-z aggregation coordinate set of the core point Y is greater than or equal to the X range matching degree PP x Judging that the X-Y aggregate coordinate set of the core point X and the X-z aggregate coordinate set of the core point Y can form a stable server group, and combining the X-Y aggregate coordinate set of the core point X and the X-z aggregate coordinate set of the core point Y to generate the stable server group; if the matching degree of the X range of the X-Y aggregate coordinate set of the core point X and the X range of the X-z aggregate coordinate set of the core point Y is smaller than the X range matching degree PP x Judging that the X-Y aggregate coordinate set of the core point X and the X-z aggregate coordinate set of the core point Y cannot form a stable server group without any operation;
setting a distance threshold JL and a kernel judging threshold HF;
the process of obtaining the geometric distance between the stable server groups is as follows:
obtaining a geometric coordinate extremum of a stable server group, wherein the geometric coordinate extremum comprises an x maximum value, an x minimum value, a y maximum value, a y minimum value, a z maximum value and a z minimum value; the x maximum value is the maximum value in x coordinate values of the stable servers existing in the stable server group, and the rest geometrical coordinate extremum is the same;
two-point distance formula through three-dimensional space Obtaining the geometric distance between each stable server group;
if stable server group A and stable server group BThe geometric distance between them is Ls A-B If the distance is larger than the distance threshold JL, no relation exists between the stable server group A and the stable server group B;
if the geometric distance between the stable server group A and the stable server group B is Ls A-B Less than or equal to the distance threshold JL, andif the number is greater than or equal to 1, judging that the stable server group A is a core cluster of the stable server group B, wherein the stable server group B is a radiation cluster of the stable server group A;
If the geometric distance between the stable server group A and the stable server group B is LsA -B Less than or equal to the distance threshold JL, ifIf the number of the radiation machines is smaller than 1, judging that the stable server group A is a radiation machine group of the stable server group B, wherein the stable server group B is a core machine group of the stable server group A;
if there is a stable server cluster that is not the core cluster or the radiation cluster of any other stable server cluster, determining that the stable server cluster is an edge cluster;
example 5
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the step 2 of grading the stable server group by calculation force comprises the following steps:
the stable server group is internally provided with a calculation force data storage unit which is used for storing the MAC address, calculation force and calculation force grade of the stable server; the MAC address is the MAC address of the stable server, the calculation force is the calculation force of the stable server, and the calculation force grade is the calculation force grade corresponding to the stable server; one MAC address corresponds to one calculation force and one calculation force grade, and the three are in one-to-one correspondence;
The computing power is data obtained by computing the bit rate, concurrency, throughput, time delay and channel utilization rate of the stable server group through a computing power formula;
the calculation force grade is the grade obtained according to calculation force division;
the calculation force formula is
Wherein bits is bit rate, cont is concurrency, thro is throughput, delay is time delay, and avail is channel utilization;
acquiring bit rate, concurrency, throughput, time delay and channel utilization rate of a stable server, and obtaining calculation power Emg of the stable server through a calculation power formula;
acquiring the MAC address and the computing power Emg of the stable server, and storing the MAC address and the computing power Emg into a computing power data storage unit;
setting a computing power update period Timey;
updating the computing power data storage unit according to the computing power updating period Timey;
the bit rate, the concurrency, the throughput, the time delay and the channel utilization rate of the stable server are obtained regularly, a new calculation force Emg 'is obtained through a calculation force formula, and the calculation force Emg in the calculation force data storage unit is replaced by the calculation force Emg' according to the MAC address of the stable server, so that the effect of updating the calculation force data storage unit is achieved;
setting a calculation force level threshold DJ 1 、DJ 2 、DJ 3 And DJ 1 <DJ 2 <DJ 3 ；
If the calculation power Emg of the stable server is less than or equal to DJ 1 The stable server is a first-level computing power server, and the computing power level of the stable server is recorded as a first level;
if the computing power Emg of the stable server is greater than DJ 1 And less than or equal to DJ 2 The stable server is a second-level computing power server, and the computing power level of the stable server is recorded as a second level;
if the computing power Emg of the stable server is greater than DJ 2 And less than or equal to DJ 3 The stable server is a three-level computing power server, and the computing power level of the stable server is recorded as three levels;
if the computing power Emg of the stable server is greater than DJ 3 The stable server is a four-level power calculation server, and the power calculation level of the stable server is recorded as four levels;
example 6
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the step 3 of grading processing of the deterministic network authorized service comprises the following steps:
the stable server group is internally provided with a service storage unit for storing specific information of services, wherein the specific information comprises a home code, a service model, service content, service volume and service grade; the home code is used for indicating the subordinate company of the service; the service model is used for indicating the service type, for example, if the service model is 001, the service is indicated to be a storage file service; the service content is a specific content record in service interaction; the traffic is used for indicating the data size of the service content, for example, the service generates 200MB of service content in the interaction process, and the traffic is recorded as 200MB;
Classifying the service according to the service volume, the submitting frequency, the service weight and the attribution weight of the service;
calculating the service volume, the submitting frequency, the service weight and the attribution weight of the service through a service grading formula Wog =XH+MaxMp×Ms, obtaining a service grade weight Wog, and grading the service according to a service grade weight Wog;
wherein XH is service weight, ma is traffic, mp is delivery frequency, ms is attribution weight;
the service weight is assigned according to the service model, the service volume is the service volume in the service storage unit, the submitting frequency is obtained through calculation of the service storage unit according to a frequency formula, and the attribution weight is assigned according to the attribution code;
wherein the frequency formula isWherein Muc is a frequency period, and Mtime is the number of times of processing the service in the frequency period;
for example, if the frequency period Muc is 30 days and the frequency formula is used for obtaining the submitting frequency of the service a by 2023, 5 months and 1 day, then submitting the query request to the service storage unit to obtain the transacting times Mtimes of the service a from 2023, 4 months and 1 day to 2023, 5 months and 1 day; by frequency formulaCalculating to obtain the submitting frequency of the service A as Mp;
setting a service class threshold WD 1 、WD 2 And WD 3 And WD 1 <WD 2 <WD 3 ；
If the service grade Wog of the service is less than or equal to WD 1 The service is a first-level service, and the service level of the service is recorded as a first level;
if the traffic class Wog of the traffic is greater than WD 1 And is smaller than WD 2 The service is a secondary service, and the service class of the service is marked as a secondary service;
if the traffic class Wog of the traffic is greater than WD 2 And is smaller than WD 3 The service is a three-level service, and the service level of the service is recorded as three levels;
if the traffic class Wog of the traffic is greater than WD 3 The service is a four-level service, and the service level of the service is marked as four-level;
setting a service level update period WTY;
according to the service level update period WTY, periodically updating the service level;
example 7
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the matching process of the service and the stable server group in the step 3 is as follows:
if the stable server group receives the first-level service, searching a first-level computing power server for processing; if the stable server group receives the secondary service, a secondary computing power server is searched for processing; if the stable server group receives the three-level service, searching a three-level computing power server for processing; if the stable server group receives the fourth-level service, searching a fourth-level computing power server for processing;
If the computing power server corresponding to the current service level does not have idle resources, namely, the primary computing power server does not have a server capable of processing primary service, the superior computing power server is applied to process the service; if the superior computing power server does not have the idle resources, the superior computing power server of the superior computing power server is applied to process the service until the highest computing power server is requested;
the four-level power calculation server is an upper-level power calculation server of the three-level power calculation server, the three-level power calculation server is an upper-level power calculation server of the two-level power calculation server, the two-level power calculation server is an upper-level power calculation server of the one-level power calculation server, and the four-level power calculation server is a highest-level power calculation server;
if the highest-level computing power server still has no idle resources, generating first-level early warning information to inform a user of insufficient computing power, automatically screening services managed by the stable server group, marking the service wasting the resources as a stream service, and performing migration processing on the stream service;
example 8
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
In step 3, if the stable server has a situation of insufficient computing power, the service wasting the resources is marked as a streaming service, and the streaming service is migrated, and the identification process of the streaming service is as follows:
setting a streaming threshold LF;
acquiring the submitting frequency Mp of the service through a frequency formula according to the service storage unit;
according to the formula of the discharge weightAcquiring the streaming weight Q of a service lf ；
Wherein XH is service weight, mp is delivery frequency, ms is attribution weight;
if the traffic has a streaming weight Q lf If the service model number is larger than the play threshold LF, marking the service as a play service, and marking the attribution code and the service model number of the service as a play index;
if the traffic has a streaming weight Q lf If the traffic is smaller than or equal to the play threshold LF, no operation is needed to be performed on the traffic;
example 9
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the migration processing procedure in the step 3 comprises the following steps:
generating a streaming request according to the streaming index, and submitting the streaming request to a service storage unit;
after receiving the stream playing request, the service storage unit inquires the service according to the stream playing index and generates a stream playing service set;
Generating a migration application according to the streaming service set, submitting the migration application to a radiation machine group of the stable server group, generating migration permission information according to an MAC address of the radiation machine group if the radiation machine group agrees to migrate, sending the migration permission information to the stable server group, and returning migration refusal information if the radiation machine group disagrees to migrate;
if the stable server group receives migration permission information, marking a radiation machine group to which the MAC address belongs as a target machine group according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target machine group;
if the stable server group does not receive the migration permission information, namely the received replies are migration refusal information, a migration application is sent to a core cluster of the stable server group; if the core machine group agrees to migrate, the core machine group generates migration permission information according to the self MAC address and sends the migration permission information to the stable server group, and if the core machine group disagrees to migrate, the core machine group returns migration refusal information;
if the stable server group receives migration permission information, marking a core cluster to which the MAC address belongs as a target cluster according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target cluster;
If the stable server group does not receive the migration permission information, namely the received replies are migration refusal information, a migration application is sent to the edge cluster with the closest geometric distance; if the edge cluster agrees to migrate, the edge cluster generates migration permission information according to the self MAC address and sends the migration permission information to the stable server cluster, and if the edge cluster does not agree to migrate, the edge cluster returns migration refusal information;
if the stable server group receives migration permission information, marking an edge cluster to which the MAC address belongs as a target cluster according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target cluster;
if the stable server group receives the refused migration information, generating secondary early warning information, informing the user that the computing power is seriously insufficient, and taking corresponding measures by the user;
example 10
On the implementation level, on the basis of embodiment 1, this embodiment further specifically describes, with reference to fig. 1, a deterministic network-based network maintenance method in embodiment 1:
the process of implementing the corresponding adjustment measure according to the interaction stage in the step 4 comprises the following steps:
marking a stable server group for transmitting the streaming service set as a source server group, and marking a stable server group for receiving the streaming service set as a target server group;
When migration processing is carried out on the streaming service, if the streaming service is detected at a server port of the source server group, namely the home code and the service model of the existing service are detected to be consistent with the home code and the service model of the streaming service at the server port of the source server group, the streaming service is judged to be the interactive service;
for example, there is a play service a, the home code of the play service a is 01000101, the service model 003, before the play service a is migrated, a server port is detected, if the home code of the service a is 01000101 and the service model 003 is detected, the play service a exists in the server port, and the play service a is determined as an interactive service;
the interaction stage of the interaction service comprises a handshake stage, a processing stage and a waving stage;
if the interactive service is in the handshake phase, sending refusal connection information to a stable server submitting the interactive service, generating connection change information according to the IP address of the target server group, and sending the connection change information to the stable server submitting the interactive service; meanwhile, the source server group packages and sends the local data of the interactive service to the target server group, wherein the local data is the service specific information of the home code, the service model and the interactive service in the service storage unit; the source server group packages and sends the local data to the target server group, the target server group sends a receiving success signal to the source server group after receiving the receiving success signal, and the source server group deletes the local data after receiving the receiving success signal;
If the interactive service is in the processing stage, carrying out 'side processing, side migration and side verification'; the method comprises the steps that an origin server group processes interactive services according to a normal processing flow, meanwhile, the origin server group cuts local data of the interactive services to obtain data fragments, copies the data fragments to generate copy fragments, packages the copy fragments to be sent to a target server group, copies the copy fragments after receiving the copy fragments to generate check data, packages the check data to the origin server group, compares the check data with the data fragments after receiving the check data, cuts, copies, packages and sends the next time if the comparison result is the same, sends error signals to the target server group to delete the data fragments if the comparison result is different, and repacks and sends the data fragments; after the migration processing of the interactive service is finished, the target server group splices the received plurality of copy fragments according to the receiving sequence to generate copy data, copies the copy data to generate check data, sends the check data to the source server group, compares the check data with the local data after the source server group receives the check data, sends a migration success signal to the target server group if the comparison result is the same, and deletes the local data; if the comparison results are different, the local data are packaged and sent to a target server group, after the target server group receives the signals successfully, the target server group sends the signals successfully received to a source server group, and after the source server group receives the signals successfully received, the local data are deleted;
If the interactive service is in the waving stage, waiting for the waving of the interactive service to finish, namely disconnecting; after the waving is finished, the source server group packages and transmits the local data of the interactive service to the target server group, the target server group transmits a successful receiving signal to the source server group after receiving the successful receiving signal, and the source server group deletes the local data after receiving the successful receiving signal;
the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A deterministic network-based network maintenance method, comprising the steps of:
step 1: setting a deterministic network, screening servers conforming to the transacted deterministic network service according to the deterministic network, and marking the servers conforming to the transacted deterministic network service as stable servers;
Step 2: obtaining a stable server group according to the distribution condition of the stable servers, wherein the stable server group consists of a core machine group, a radiation machine group and an edge machine group, and carrying out grading treatment on the stable server group according to the calculation power of the stable server group;
step 3: the service authorized by the deterministic network is classified, and the stable server group corresponding to the class is matched according to the class of the service, so that the service can be efficiently and stably processed; if the stable server group has the condition of insufficient calculation power, screening the services managed by the stable server group, marking the services wasting the calculation power of the stable server as stream play services, and performing migration processing on the stream play services so as to ensure that the stable server can operate efficiently and stably;
step 4: when migration processing is carried out on the streaming service, if the streaming service is detected at the port of the stable server, the streaming service is judged to be an interactive service, and the interactive service is the service under processing; if the interactive service exists, corresponding adjustment measures are implemented according to the interactive stage where the interactive service is located.
2. The deterministic network-based network maintenance method according to claim 1, wherein the process of setting up the deterministic network comprises:
Training the demand data and the capacity data through a convolutional neural network, a depth residual error network and a transducer model to obtain a deterministic network generation algorithm; the demand data is input and acquired by a user; the capability data is the performance data of the server;
setting a network service period; the user carries out network deployment according to the deterministic network generated by the deterministic network generation algorithm, generates network quality parameters through a network use period, judges whether the network quality of the deterministic network is qualified or not through the network quality parameters, can continue to use if the network quality is qualified, and can not continue to use if the network quality is unqualified.
3. The deterministic network-based network maintenance method according to claim 2, wherein the process of acquiring the stable server is:
establishing a space rectangular coordinate system;
obtaining the geographic position of a stable server;
acquiring the geometric position of a stable server according to the geographic position;
according to the geometric positions of the stable servers, obtaining the x-y distance and the x-z distance between the stable servers, and generating an x-y set and an x-z set;
acquiring an x-y aggregation coordinate set of the stable server according to the x-y aggregation coordinate set through the x range overlap ratio, and acquiring an x-z aggregation coordinate set of the stable server according to the x-z aggregation coordinate set;
Judging whether a stable server group can be formed according to the x-y aggregation coordinate set and the x-z aggregation coordinate set of the stable server through the x range matching degree; if the stable server group can be formed, combining the x-y aggregation coordinate set and the x-z aggregation coordinate set to generate the stable server group; if the stable server group cannot be formed, no operation is needed;
and generating a core cluster, a radiation cluster and an edge cluster according to the geometric distance and the magnitude order among the stable server clusters.
4. A deterministic network-based network maintenance method according to claim 3, wherein the process of hierarchical processing of the stable server farm according to computational effort is:
acquiring bit rate, concurrency, throughput, time delay and channel utilization rate of a stable server, and obtaining calculation power of the stable server through a calculation power formula;
setting a calculation force level threshold, and judging the level class of the stable server according to the calculation force level threshold and the calculation force; the rank categories include: the system comprises a first-level computing power server, a second-level computing power server, a third-level computing power server and a fourth-level computing power server.
5. The deterministic network-based network maintenance method according to claim 4, wherein the service classification process comprises:
The stable server group is internally provided with a service storage unit for storing specific information of services, wherein the specific information comprises a home code, a service model, service content, service volume and service grade;
calculating the business volume, submitting frequency, business weight and attribution weight of the business through a business grading formula, obtaining business grade weight, and grading the business according to the business grade weight;
the service weight is assigned according to the service model, the service volume is the service volume in the service storage unit, the submitting frequency is obtained through calculation of the service storage unit according to a frequency formula, and the attribution weight is assigned according to the attribution code;
setting a service grade threshold, and judging the grade category of the service according to the service grade threshold and the service grade weight; the rank categories include: primary, secondary, tertiary and quaternary services.
6. The network maintenance method based on deterministic network according to claim 5, wherein the matching process of the stable server group corresponding to the service level matching level is:
the first-level business is processed by a first-level computing power server; the second-level business is processed by a second-level computing power server; the third-level business is processed by a third-level computing power server; the fourth-level business is processed by a fourth-level computing power server;
If the computing power server corresponding to the current service level does not have idle resources, the superior computing power server is applied to process the service; if the superior computing power server does not have the idle resources, the superior computing power server of the superior computing power server is applied to process the service until the highest computing power server is requested;
the upper-level computing power server is a server with the computing power level higher than that of the current computing power server;
the highest power calculating server is the highest-level power calculating server;
if the highest-level computing power server still has no idle resources, generating first-level early warning information to inform a user of insufficient computing power, automatically screening services managed by the stable server group, marking the service wasting the resources as a streaming service, and performing migration processing on the streaming service.
7. The deterministic network-based network maintenance method according to claim 6, wherein the identification procedure of the streaming service is:
setting a release threshold;
acquiring the streaming weight of the service according to the streaming weight formula;
if the traffic stream weight is greater than the stream threshold, marking the traffic as stream traffic and marking the attribution code and the traffic model of the traffic as stream index;
If the traffic flow weight is less than or equal to the flow threshold, no operation is needed for the traffic.
8. The deterministic network-based network maintenance method according to claim 7, wherein the migration process is as follows:
generating a streaming request according to the streaming index, and submitting the streaming request to a service storage unit;
the service storage unit inquires the service according to the stream index and generates a stream service set;
generating a migration application according to the streaming service set, submitting the migration application to a radiation machine group of the stable server group, generating migration permission information according to an MAC address of the radiation machine group if the radiation machine group agrees to migrate, sending the migration permission information to the stable server group, and returning migration refusal information if the radiation machine group disagrees to migrate;
if the stable server group receives migration permission information, marking a radiation machine group to which the MAC address belongs as a target machine group according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target machine group;
if the replies received by the stable server group are refusal migration information, a migration application is sent to a core cluster of the stable server group; if the core machine group agrees to migrate, the core machine group generates migration permission information according to the self MAC address and sends the migration permission information to the stable server group, and if the core machine group disagrees to migrate, the core machine group returns migration refusal information;
If the stable server group receives migration permission information, marking a core cluster to which the MAC address belongs as a target cluster according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target cluster;
if the replies received by the stable server group are refusal migration information, sending a migration application to the edge cluster with the closest geometric distance; if the edge cluster agrees to migrate, the edge cluster generates migration permission information according to the self MAC address and sends the migration permission information to the stable server cluster, and if the edge cluster does not agree to migrate, the edge cluster returns migration refusal information;
if the stable server group receives migration permission information, marking an edge cluster to which the MAC address belongs as a target cluster according to the MAC address in the migration permission information, and packaging and sending a stream service set to the target cluster;
if the stable server group receives the refused migration information, generating second-level early warning information, informing the user that the computing power is seriously insufficient, and taking corresponding measures by the user.
9. The deterministic network-based network maintenance method according to claim 8, wherein the process of implementing the corresponding adjustment measure according to the interaction phase comprises:
The interaction stage of the interaction service comprises a handshake stage, a processing stage and a waving stage;
marking a stable server group for transmitting the streaming service set as a source server group, and marking a stable server group for receiving the streaming service set as a target server group;
if the interactive service is in the handshake phase, sending refusal connection information to a stable server submitting the interactive service, generating connection change information according to the IP address of the target server group, and sending the connection change information to the stable server submitting the interactive service; meanwhile, the source server group packages and sends the local data of the interactive service to the target server group, wherein the local data is the service specific information of the home code, the service model and the interactive service in the service storage unit; the source server group packages and sends the local data to the target server group, the target server group sends a receiving success signal to the source server group after receiving the receiving success signal, and the source server group deletes the local data after receiving the receiving success signal;
if the interactive service is in the processing stage, carrying out 'side processing, side migration and side verification'; the method comprises the steps that an origin server group processes interactive services according to a normal processing flow, meanwhile, the origin server group cuts local data of the interactive services to obtain data fragments, copies the data fragments to generate copy fragments, packages the copy fragments to be sent to a target server group, copies the copy fragments after receiving the copy fragments to generate check data, packages the check data to the origin server group, compares the check data with the data fragments after receiving the check data, cuts, copies, packages and sends the next time if the comparison result is the same, sends error signals to the target server group to delete the data fragments if the comparison result is different, and repacks and sends the data fragments; after the migration processing of the interactive service is finished, the target server group splices the received plurality of copy fragments according to the receiving sequence to generate copy data, copies the copy data to generate check data, sends the check data to the source server group, compares the check data with the local data after the source server group receives the check data, sends a migration success signal to the target server group if the comparison result is the same, and deletes the local data; if the comparison results are different, the local data are packaged and sent to a target server group, after the target server group receives the signals successfully, the target server group sends the signals successfully received to a source server group, and after the source server group receives the signals successfully received, the local data are deleted;
If the interactive service is in the waving stage, waiting for the waving of the interactive service to finish, namely disconnecting; after the waving is finished, the source server group packages and sends the local data of the interactive service to the target server group, the target server group sends a successful receiving signal to the source server group after receiving the successful receiving signal, and the source server group deletes the local data after receiving the successful receiving signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311530243.1A CN117376081B (en) | 2023-11-16 | 2023-11-16 | Network maintenance method based on deterministic network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311530243.1A CN117376081B (en) | 2023-11-16 | 2023-11-16 | Network maintenance method based on deterministic network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117376081A true CN117376081A (en) | 2024-01-09 |
| CN117376081B CN117376081B (en) | 2024-08-06 |
Family
ID=89402359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311530243.1A Active CN117376081B (en) | 2023-11-16 | 2023-11-16 | Network maintenance method based on deterministic network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117376081B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507650A (en) * | 2020-07-02 | 2020-08-07 | 深圳微品致远信息科技有限公司 | Computing power distribution scheduling method and system for edge computing platform |
| CN114363187A (en) * | 2021-07-16 | 2022-04-15 | 网络通信与安全紫金山实验室 | Deployment method and system of virtual industrial equipment nodes |
| CN115203867A (en) * | 2022-06-21 | 2022-10-18 | 联通(上海)产业互联网有限公司 | Calculation power distribution system based on dynamic calculation power domain screening |
| WO2023082815A1 (en) * | 2021-11-09 | 2023-05-19 | 中兴通讯股份有限公司 | Method and apparatus for constructing deterministic routing, and storage medium |
| CN116896562A (en) * | 2023-07-28 | 2023-10-17 | 中国信息通信研究院 | Application layer deterministic service resource scheduling method and system |
-
2023
- 2023-11-16 CN CN202311530243.1A patent/CN117376081B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507650A (en) * | 2020-07-02 | 2020-08-07 | 深圳微品致远信息科技有限公司 | Computing power distribution scheduling method and system for edge computing platform |
| CN114363187A (en) * | 2021-07-16 | 2022-04-15 | 网络通信与安全紫金山实验室 | Deployment method and system of virtual industrial equipment nodes |
| WO2023082815A1 (en) * | 2021-11-09 | 2023-05-19 | 中兴通讯股份有限公司 | Method and apparatus for constructing deterministic routing, and storage medium |
| CN115203867A (en) * | 2022-06-21 | 2022-10-18 | 联通(上海)产业互联网有限公司 | Calculation power distribution system based on dynamic calculation power domain screening |
| CN116896562A (en) * | 2023-07-28 | 2023-10-17 | 中国信息通信研究院 | Application layer deterministic service resource scheduling method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117376081B (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110933072B (en) | Data transmission method and device based on block chain and electronic equipment | |
| Conner et al. | A trust management framework for service-oriented environments | |
| Jiang et al. | Catchsync: catching synchronized behavior in large directed graphs | |
| CN110858804B (en) | Method for determining certificate status | |
| CN105447113B (en) | A kind of information analysis method based on big data | |
| CN110619019B (en) | Distributed storage method and system for data | |
| CN105354251B (en) | Electric power cloud data management indexing means based on Hadoop in electric system | |
| CN114189347B (en) | Data safety transmission method combining data granulation and gatekeeper | |
| CN112199412B (en) | Payment bill processing method based on block chain and block chain bill processing system | |
| CN112149967A (en) | Power communication network vulnerability assessment method and system based on complex system theory | |
| CN106803096A (en) | A kind of short message type recognition methods, system and short message managing platform | |
| CN112351088A (en) | CDN cache method, device, computer equipment and storage medium | |
| CN111966967A (en) | Copyright storage method and system based on block chain technology and CDN | |
| CN112766560B (en) | Alliance blockchain network optimization method, device, system and electronic equipment | |
| CN117376081B (en) | Network maintenance method based on deterministic network | |
| CN113792892A (en) | Federal learning modeling optimization method, apparatus, readable storage medium, and program product | |
| CN107357557A (en) | A kind of information updating method and device | |
| CN116186629B (en) | Financial customer classification and prediction method and device based on personalized federal learning | |
| CN109981726A (en) | A kind of distribution method of memory node, server and system | |
| CN117216736A (en) | Abnormal account identification method, data scheduling platform and graph computing platform | |
| US20230029312A1 (en) | Similarity-based search for fraud prevention | |
| CN112734466A (en) | Method and device for processing associated information and storage medium | |
| CN108234434B (en) | Detection method based on email address identification | |
| CN115269126B (en) | Cloud platform inverse affinity scheduling system based on cosine similarity | |
| CN111275348A (en) | Electronic order information processing method, server and electronic order information processing system |
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 |