CN115203867A - Calculation power distribution system based on dynamic calculation power domain screening - Google Patents
Calculation power distribution system based on dynamic calculation power domain screening Download PDFInfo
- Publication number
- CN115203867A CN115203867A CN202210702690.XA CN202210702690A CN115203867A CN 115203867 A CN115203867 A CN 115203867A CN 202210702690 A CN202210702690 A CN 202210702690A CN 115203867 A CN115203867 A CN 115203867A
- Authority
- CN
- China
- Prior art keywords
- computing power
- power supply
- domain
- computing
- dynamic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012216 screening Methods 0.000 title claims abstract description 48
- 238000005070 sampling Methods 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims description 19
- RYAUSSKQMZRMAI-YESZJQIVSA-N (S)-fenpropimorph Chemical compound C([C@@H](C)CC=1C=CC(=CC=1)C(C)(C)C)N1C[C@H](C)O[C@H](C)C1 RYAUSSKQMZRMAI-YESZJQIVSA-N 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 5
- 230000002035 prolonged effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 108020001568 subdomains Proteins 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of computing power networks, in particular to a computing power distribution system based on dynamic computing power domain screening, which comprises a dynamic computing power domain system, a dynamic computing power domain screening period and a sampling rule, wherein the dynamic computing power domain system comprises a dynamic computing power domain system refreshing period and a sampling rule; however, in the computational power network, the geographic location is not important, and cannot represent the delay index of the computational power supply node, and the computational power supply node screening error is easily caused in a delay sensitive service scene.
Description
Technical Field
The invention relates to the technical field of computing power networks, in particular to a computing power distribution system based on dynamic computing power domain screening.
Background
In the prior art, when a computing power domain is constructed, the distance between the geographical position of a computing power supply node and a computing power demand side is mainly considered as a basis for screening the computing power supply node; however, in the computational power network, the geographic location is not important, and cannot represent the delay index of the computational power supply node, and the computational power supply node screening error is easily caused in a delay sensitive service scene.
In summary, the present invention solves the existing problems by designing a computing power distribution system based on dynamic computing power domain screening.
Disclosure of Invention
The present invention is directed to a computing power distribution system based on dynamic computing power domain screening, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a computing power distribution system based on dynamic computing power domain screening comprises a dynamic computing power domain system, and dynamic computing power domain screening and computing power distribution, and is characterized in that: the dynamic computational power domain system comprises a dynamic computational power domain system refreshing period and a sampling rule;
the dynamic computing power domain system belongs a certain computing power supply node to a certain computing power domain according to four dimensions of time delay, bandwidth, computing power and a machine room/subnet, refreshes the computing power domain system according to real-time changes of computing tasks and network conditions in the computing power network, and refreshes the domain affiliation of the computing power supply node at the same time, wherein the four dimensions related to the computing power domain system are irrelevant to the geographical position of the computing power supply node;
the state computation force domain system refreshing period and the sampling rule are as follows:
1) The dynamic force domain computing system carries out periodic refreshing according to actual needs, wherein the period can be customized, such as: reporting the state of each computational power supply node in the system periodically through an external interface for 1 second;
2) Dynamic force domain system sampling rule:
a. considering that indexes such as time delay, bandwidth and computational power change rapidly along with time, the numerical value of a certain period cannot effectively reflect the state of a computational power supply node, and misjudgment of a computational power demand side is easily caused, so a sampling rule is set according to actual needs, a plurality of periodic numerical values are sampled within a certain time span, a percentage threshold value is set, and a qualified computational power supply node which is greater than the threshold value is as follows: refreshing the period for 1 second, continuously sampling for 10 periods, wherein when the value more than 8 periods falls on Y1, D2 and S3, the computational power supply node is qualified;
b. the index of the computer room/subnet is not obvious in change along with time, namely, the index changes only when the computing power supply node is moved by a server or when the subnet is planned to change, so that the numerical value of the computer room/subnet domain can be judged whether the computing power supply node is qualified or not only by sampling 1 cycle;
the dynamic computing power domain screening and computing power distribution:
the screening of the dynamic calculation power domain firstly depends on the service type, and the scheme divides the calculation service into two types and a service process;
1) Delay sensitive services: in this kind of service, it is desirable to obtain a calculation result faster, and it is required that the result reliability of each time is high, that is, because there is no extra time for recalculation, the result speed is affected, except network delay, and transmission bandwidth is also included, that is, under the condition that bandwidth cannot be guaranteed, the result return time is inevitably prolonged, and reliability is guaranteed, a calculation power task can be sliced first, and then each slice is redundantly sent to different calculation power supply nodes for calculation, so that the problem caused by the failure of single slice calculation can be effectively avoided, and a specific dynamic calculation power domain screening and calculation power distribution rule is described as follows:
a. in the delay sensitive service, when the computing power supply node G1 is screened in the dynamic computing power domain, it needs to simultaneously satisfy that G1 falls in a certain sub-domain of the delay domain-Y and the bandwidth domain-D, for example: g1 ∈ (Y1, D2); and when the slice redundancy is issued to the next computation power supply node G2, considering the reliability requirement, in order to avoid a fault of a certain machine room/subnet, different redundancy computation tasks of the same slice may not be carried in the same machine room/subnet, that is, G2 and G1 may not belong to the same sub-domain of the machine room/subnet domain-J at the same time, for example: g1 belongs to J1, G2 belongs to J2;
b. when the computational power supply nodes simultaneously meet the screening rules of time delay, bandwidth and machine room/subnet and can screen enough qualified computational power supply nodes, the computational power supply nodes enter the screening process of a computational power domain-S; if the task time can not be met simultaneously, repeatedly sampling N rounds under the condition that the service is allowed, wherein the specific number of rounds can be configured, and if the task time can not be met simultaneously all the time, the task time fails;
c. in the screening process of the computing power domain-S, matching computing power rules within the range of qualified computing power supply nodes selected in the last step according to the number of computing power task slices, the redundancy requirement number and the computing power required by each slice, and starting a computing task if enough computing power supply nodes can be matched; if the sufficient computing power supply node cannot be matched, under the condition that the service is allowed, repeatedly sampling N rounds, wherein the specific number of rounds can be configured, and if the specific number of rounds cannot be met at the same time all the time, the task fails overtime;
2) Service insensitive to time delay: such services only need to obtain a correct calculation result and can tolerate recalculation after a result error, so that only a proper calculation power supply node needs to be matched in a calculation power domain, and a specific dynamic calculation power domain screening and calculation power distribution rule is described as follows:
a. directly entering a screening process of a computational power domain-S, selecting qualified computational power supply nodes in the computational power domain-S according to the number of computational power task slices without setting redundant computation and the computational power required by each slice, matching computational power rules, and starting a computational task if enough computational power supply nodes can be matched; if the sufficient computing power supply nodes cannot be matched, under the condition that the service allows, the N rounds of repeated sampling are carried out, the specific number of rounds can be configured, and if the specific number of rounds cannot be met all the time, the task is failed to be overtime.
As a preferred embodiment of the present invention, the four dimensions are defined as follows:
a. time delay: network time delay from the computing power demand side to the computing power supply node;
b. bandwidth: the guaranteed transmission bandwidth from the computing power demand side to the computing power supply node;
c. calculating the strength: the current computing power allowance of the computing power supply node;
d. machine room/subnet: and calculating the machine room ID where the power supply node is positioned, or the subnet ID.
The dynamic force calculation domain system is updated in real time according to calculation tasks and network conditions in the force calculation network, and the corresponding relation between the force calculation supply nodes and each force calculation domain at a certain moment is synchronously updated in real time.
Compared with the prior art, the invention has the beneficial effects that:
1. in the invention, through designing and comprehensively considering indexes such as network delay, bandwidth detection, calculation power supply, machine rooms/subnetworks and the like, a multi-dimensional dynamic calculation power domain system is constructed, and a reasonable sampling method is set according to the periodically reported state of the system, so that the aim of accurately evaluating and screening calculation power supply nodes is fulfilled, and the problem that the distance between the geographical position where the calculation power supply node is located and a calculation power demand side is mainly considered when a calculation power domain is constructed in the prior art is effectively solved and is used as a basis for screening the calculation power supply node; however, in the computational power network, the geographic location is not important, and cannot represent the delay index of the computational power supply node, and the computational power supply node screening error is easily caused in a delay sensitive service scene.
Drawings
FIG. 1 is a schematic structural diagram of a corresponding relationship between a computational power supply node and each computational power domain at a certain time;
fig. 2 is a schematic diagram of a type business process participation flow structure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without any creative work based on the embodiments of the present invention belong to the protection scope of the present invention.
While several embodiments of the present invention will be described more fully hereinafter with reference to the accompanying drawings, in order to facilitate an understanding of the invention, the invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, but rather should be construed to provide a more complete disclosure of the invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present, that when an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present, and that the terms "vertical", "horizontal", "left", "right" and the like are used herein for descriptive purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the terms used herein in the specification of the present invention are for the purpose of describing particular embodiments only and are not intended to limit the present invention, and the term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1-2, the present invention provides a technical solution:
a computing power distribution system based on dynamic computing power domain screening comprises a dynamic computing power domain system and dynamic computing power domain screening and computing power distribution, wherein the dynamic computing power domain system comprises a refreshing period of the dynamic computing power domain system and a sampling rule:
the computational power domain system in the scheme is characterized in that a certain computational power supply node is attributed to a certain computational power domain according to four dimensions of time delay, bandwidth, computational power and a machine room/subnet, the computational power domain system is refreshed according to real-time changes of computational tasks and network conditions in the computational power network, and domain attribution of the computational power supply node is refreshed at the same time.
The four dimensions are defined as follows:
1. time delay: network time delay from the computing power demand side to the computing power supply node;
2. bandwidth: the guaranteed transmission bandwidth from the computing power demand side to the computing power supply node;
3. calculating the strength: the current computing power allowance of the computing power supply node;
4. machine room/subnet: the computer room ID or the subnet ID where the computing power supply node is located;
it should be noted that the four dimensions involved in the computational power domain system of the present solution are independent of the geographic location of the computational power supply node (for example, the computational power demand party a is in beijing, the computational power supply node B is in shanghai, and the computational power supply node C is in hebei, but there is a special optical fiber line between a and B directly connected, and a common network line between a and C is switched through a plurality of switches, so in the present solution, although C is closer than the physical location of B, the delay and bandwidth of B are obviously superior);
in the implementation process of the scheme, four computing power domains and respective sub-domain systems are constructed according to four dimensions of time delay, bandwidth, computing power and a machine room/sub-network, the same computing power supply node possibly belongs to different computing power domains/sub-domains at different time points, the whole dynamic computing power domain system is updated in real time according to computing tasks and network conditions in the computing power network, and the corresponding relation between the computing power supply node and each computing power domain at a certain moment is shown in figure 1;
a dynamic computational force domain system refresh period, and a sampling rule:
1. the dynamic computing power domain system periodically refreshes (the period can be self-defined, such as 1 second) according to actual needs, and periodically reports the state of each computing power supply node in the system through an external interface;
2. dynamic force domain system sampling rules:
(1) considering that indexes such as time delay, bandwidth and computational power change rapidly along with time, numerical values in a certain period cannot effectively reflect the state of a computational power supply node, and misjudgment of a computational power demand side is easily caused, a sampling rule is set according to actual needs, a plurality of periodic numerical values are sampled in a certain time span, a percentage threshold value is set, and a computational power supply node which is greater than the threshold value is qualified (for example, a refresh period is 1 second, 10 periods are continuously sampled, and when values greater than 8 periods fall in Y1, D2 and S3, the computational power supply node is qualified);
(2) the index of the computer room/subnet does not change obviously with time (only when the computational power supply node is moved by a server or when the subnet planning changes), so that the numerical value of the computer room/subnet domain only needs to be sampled for 1 period to judge whether the computational power supply node is qualified;
2. dynamic computing power domain screening and computing power distribution
The dynamic calculation power domain screening method comprises the steps that firstly, calculation services are divided into two types according to service types, and the service process is shown in a figure 2;
1) Delay sensitive services: such services are expected to obtain the calculation results more quickly, and require high reliability of the results of each time (because there is no extra time for recalculation), while affecting the rapidity of the results, besides network delay, transmission bandwidth (in case of bandwidth not guaranteed, the result return time is inevitably prolonged). And the reliability is guaranteed, the computing power task can be sliced firstly, and then each slice is sent to different computing power supply nodes for computing in a redundant mode, so that the problem caused by the failure of computing of a single slice can be effectively avoided. The specific dynamic computing power domain screening and computing power distribution rules are described as follows:
(1) delay sensitive service, when screening a computation power supply node G1 in a dynamic computation power domain, it needs to satisfy the requirement that G1 falls in a certain subdomain of a delay domain-Y and a bandwidth domain-D (e.g. G1 belongs to (Y1, D2)) at the same time, and when slice redundancy is issued to the next computation power supply node G2, considering the requirement of reliability, in order to avoid the fault of a certain machine room/subnet, different redundancy computation tasks of the same slice can not be carried in the same machine room/subnet, i.e. G2 and G1 can not belong to the same subdomain of a machine room/subnet domain-J at the same time (e.g. G1 belongs to J1, G2 belongs to J2)
(2) When the computational power supply nodes simultaneously meet the screening rules of time delay, bandwidth and computer room/subnet and can screen enough qualified computational power supply nodes, the computational power supply nodes enter the screening process of the computational power domain-S. If the task time can not be met simultaneously, under the condition that the service is allowed, repeatedly sampling N rounds (the specific number of rounds can be configured), and if the task time can not be met simultaneously all the time, the task time fails;
(3) in the screening process of the computing power domain-S, matching computing power rules within the range of qualified computing power supply nodes selected in the last step according to the number of computing power task slices, the redundancy requirement number and the computing power required by each slice, and starting a computing task if enough computing power supply nodes can be matched; if the sufficient computing power supply nodes cannot be matched, under the condition that the service is allowed, repeatedly sampling N rounds (the specific round number is configurable), and if the sufficient computing power supply nodes cannot be met all the time, the task is failed overtime;
2) Service insensitive to time delay: such services only need to obtain a correct calculation result and can tolerate recalculation after a result error, so that only a proper calculation power supply node needs to be matched in a calculation power domain, and a specific dynamic calculation power domain screening and calculation power distribution rule is described as follows:
directly entering a screening process of a computational power domain-S, selecting qualified computational power supply nodes in the computational power domain-S according to the number of computational power task slices (redundant computation amount does not need to be set) and the computational power required by each slice, matching computational power rules, and starting a computational task if enough computational power supply nodes can be matched; if the sufficient computing power supply nodes cannot be matched, repeatedly sampling N rounds (the specific number of rounds can be configured) under the condition of service permission, and if the sufficient computing power supply nodes cannot be met all the time, the task is overtime and fails, the process comprehensively considers indexes such as network delay, bandwidth detection, computing power supply, a machine room/subnet and the like through design, a multi-dimensional dynamic computing power domain system is constructed, a reasonable sampling method is set according to the periodically reported state of the system, the purpose of accurately evaluating and screening the computing power supply nodes is achieved, and the problem that the distance between the geographical position of the computing power supply node and a computing power demand side is mainly considered when the computing power domain is constructed in the prior art and is used as the basis for screening the computing power supply nodes is effectively solved; however, in the computational power network, the geographic location is not important, and cannot represent the delay index of the computational power supply node, and the computational power supply node screening error is easily caused in the delay sensitive service scene.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (2)
1. A computing power distribution system based on dynamic computing power domain screening comprises a dynamic computing power domain system, and dynamic computing power domain screening and computing power distribution, and is characterized in that: the dynamic computational power domain system comprises a dynamic computational power domain system refreshing period and a sampling rule;
the dynamic computing power domain system belongs a certain computing power supply node to a certain computing power domain according to four dimensions of time delay, bandwidth, computing power and a machine room/subnet, refreshes the computing power domain system according to real-time changes of computing tasks and network conditions in the computing power network, and refreshes the domain affiliation of the computing power supply node at the same time, wherein the four dimensions related to the computing power domain system are irrelevant to the geographical position of the computing power supply node;
the state computation force domain system refreshing period and the sampling rule are as follows:
1) The dynamic computational power domain system performs periodic refreshing according to actual needs, wherein the period can be customized, such as: 1 second, periodically reporting the state of each computational power supply node in the system through an external interface;
2) Dynamic force domain system sampling rules:
a. considering that indexes such as time delay, bandwidth and computational power change rapidly along with time, the numerical value of a certain period cannot effectively reflect the state of a computational power supply node, and misjudgment of a computational power demand side is easily caused, so a sampling rule is set according to actual needs, a plurality of periodic numerical values are sampled within a certain time span, a percentage threshold value is set, and a qualified computational power supply node which is greater than the threshold value is as follows: refreshing the period for 1 second, continuously sampling for 10 periods, wherein when the value more than 8 periods falls on Y1, D2 and S3, the computational power supply node is qualified;
b. the index of the computer room/subnet is not obvious in change along with time, namely, the index changes only when the computing power supply node is moved by a server or when the subnet is planned to change, so that the numerical value of the computer room/subnet domain can be judged whether the computing power supply node is qualified or not only by sampling 1 cycle;
the dynamic computing power domain screening and computing power distribution:
the screening of the dynamic calculation force domain firstly depends on the service type, and the scheme divides the calculation service into two types and service processes;
1) Delay sensitive traffic: in this kind of service, it is desirable to obtain a calculation result faster, and it is required that the result reliability of each time is high, that is, because there is no extra time for recalculation, the result speed is affected, except network delay, and transmission bandwidth is also included, that is, under the condition that bandwidth cannot be guaranteed, the result return time is inevitably prolonged, and reliability is guaranteed, a calculation power task can be sliced first, and then each slice is redundantly sent to different calculation power supply nodes for calculation, so that the problem caused by the failure of single slice calculation can be effectively avoided, and a specific dynamic calculation power domain screening and calculation power distribution rule is described as follows:
a. in the delay sensitive service, when the computing power supply node G1 is screened in the dynamic computing power domain, it needs to simultaneously satisfy that G1 falls in a certain sub-domain of the delay domain-Y and the bandwidth domain-D, for example: g1 ∈ (Y1, D2); and when the slice redundancy is issued to the next computation power supply node G2, considering the reliability requirement, in order to avoid a fault of a certain machine room/subnet, different redundancy computation tasks of the same slice may not be carried in the same machine room/subnet, that is, G2 and G1 may not belong to the same sub-domain of the machine room/subnet domain-J at the same time, for example: g1 belongs to J1, G2 belongs to J2;
b. when the computational power supply nodes simultaneously meet the screening rules of time delay, bandwidth and machine room/sub-network and can screen enough qualified computational power supply nodes, the computational power supply nodes enter the screening process of a computational power domain-S; if the task time can not be met simultaneously, repeatedly sampling N rounds under the condition that the service is allowed, wherein the specific number of rounds can be configured, and if the task time can not be met simultaneously all the time, the task time fails;
c. in the screening process of the computing power domain-S, matching computing power rules within the range of qualified computing power supply nodes selected in the last step according to the number of computing power task slices, the number of redundancy requirements and the computing power required by each slice, and starting a computing task if enough computing power supply nodes can be matched; if the sufficient computing power supply node cannot be matched, under the condition that the service is allowed, repeatedly sampling N rounds, wherein the specific number of rounds can be configured, and if the specific number of rounds cannot be met at the same time all the time, the task fails overtime;
2) Service insensitive to time delay: such services only need to obtain a correct calculation result and can tolerate recalculation after a result error, so that only a proper calculation power supply node needs to be matched in a calculation power domain, and a specific dynamic calculation power domain screening and calculation power distribution rule is described as follows:
a. directly entering a screening process of the computing power domain-S, selecting qualified computing power supply nodes in the computing power domain-S according to the number of computing power task slices without setting redundant computing quantity and the computing power required by each slice, matching computing power rules, and starting a computing task if enough computing power supply nodes can be matched; if the sufficient computing power supply nodes cannot be matched, under the condition that the service allows, the N rounds of repeated sampling are carried out, the specific number of rounds can be configured, and if the specific number of rounds cannot be met all the time, the task is failed to be overtime.
2. The computing power distribution system based on dynamic computing power domain screening, according to claim 1, characterized in that: the four dimensions are defined as follows:
a. time delay: network time delay from the calculation demand side to the calculation supply node;
b. bandwidth: the method comprises the following steps that (1) the computing power demand side can guarantee transmission bandwidth to a computing power supply node;
c. calculating the strength: the current computing power allowance of the computing power supply node;
d. machine room/subnet: and calculating the machine room ID where the power supply node is positioned, or the subnet ID.
The whole dynamic computing power domain system updates in real time according to computing tasks and network conditions in the computing power network, and the corresponding relation between the computing power supply nodes and each computing power domain at a certain moment is synchronously updated in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210702690.XA CN115203867A (en) | 2022-06-21 | 2022-06-21 | Calculation power distribution system based on dynamic calculation power domain screening |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210702690.XA CN115203867A (en) | 2022-06-21 | 2022-06-21 | Calculation power distribution system based on dynamic calculation power domain screening |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115203867A true CN115203867A (en) | 2022-10-18 |
Family
ID=83575841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210702690.XA Pending CN115203867A (en) | 2022-06-21 | 2022-06-21 | Calculation power distribution system based on dynamic calculation power domain screening |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115203867A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117376081A (en) * | 2023-11-16 | 2024-01-09 | 湖北邮电规划设计有限公司 | Network maintenance method based on deterministic network |
-
2022
- 2022-06-21 CN CN202210702690.XA patent/CN115203867A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117376081A (en) * | 2023-11-16 | 2024-01-09 | 湖北邮电规划设计有限公司 | Network maintenance method based on deterministic network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7827270B2 (en) | Mobility service clustering using network service segments | |
| Liew et al. | A framework for characterizing disaster-based network survivability | |
| EP3629521A1 (en) | Rating method for service node, domain name system (dns) scheduling method and server | |
| Sakic et al. | Towards adaptive state consistency in distributed SDN control plane | |
| CN105469317B (en) | A kind of reliability of power communication network analysis method | |
| CN109344014A (en) | A kind of main/standby switching method, device and communication equipment | |
| CN110011879B (en) | Sensor network safety real-time online monitoring system based on parallel filtering | |
| Zhao et al. | Scalable SDN architecture with distributed placement of controllers for WAN | |
| CN115203867A (en) | Calculation power distribution system based on dynamic calculation power domain screening | |
| US20240187765A1 (en) | Passive optical network for utility infrastructure resiliency | |
| CN109494728A (en) | A kind of distribution terminal addressing selection method | |
| CN109327401A (en) | A kind of traffic scheduling method and system of SDN network | |
| CN104488227A (en) | Method for isolated anomaly detection in large-scale data processing systems | |
| Chen et al. | Classification, Building and Orchestration Management of Digital Twin Network Models | |
| CN113660677B (en) | Maximum error independent path calculation method of weighted time-varying network under consumption limit | |
| Gu et al. | Recovery Routing Based on Q‐Learning for Satellite Network Faults | |
| CN115118635A (en) | Time delay detection method, device, equipment and storage medium | |
| Shi et al. | Operation and maintenance analysis for power communication networks based on big data | |
| Kubat | Assessing throughput and reliability in communication and computer networks | |
| Anufrenko et al. | Diagnostics of the transport data network routes with the neural networks | |
| Kanaev et al. | Model of the synchronization network functioning process in the context of intellectualization of network control functions | |
| Olajide et al. | An approach to improve the availability of a traffic light system | |
| Li et al. | Availability allocation of networked systems using Markov model and heuristics algorithm | |
| CN111049683A (en) | Attention mechanism-based large-scale network group real-time fault prediction method | |
| Varshney et al. | Multilevel fault tolerance in infrastructure‐oriented wireless networks: framework and performance evaluation |
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 |