CN113919412B - Data distribution method, device and storage medium - Google Patents
Data distribution method, device and storage medium Download PDFInfo
- Publication number
- CN113919412B CN113919412B CN202111025736.0A CN202111025736A CN113919412B CN 113919412 B CN113919412 B CN 113919412B CN 202111025736 A CN202111025736 A CN 202111025736A CN 113919412 B CN113919412 B CN 113919412B
- Authority
- CN
- China
- Prior art keywords
- data
- node
- state
- basic
- nodes
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a data distribution method, equipment and a storage medium, wherein the method comprises the steps of receiving original data and extracting corresponding basic characteristics of the original data; matching the basic features with a basic feature library, and if the matching is successful, adding the original data into a corresponding cache queue of a node to which the matched basic feature library belongs; otherwise, adding the basic features into a basic feature library of the corresponding child node according to a preset configuration rule; and after the data meets the distribution requirement, distributing the cache queue to the corresponding processing board. The invention uses the basic characteristics of the data to represent the data, and the basic characteristics are used as the data dividing basis of each distributed sub-node to ensure the clear and reliable data dividing; the central node prepares the working state of the sub-nodes, dynamically divides the data and improves the data processing efficiency; and the state feedback of the software of each child node is utilized to monitor the running state of the software in real time, so that the software is ensured to be in an effective processing capacity range, and the running efficiency of the system is improved.
Description
Technical Field
The present invention relates to the field of data management and distribution technologies, and in particular, to a data distribution method, device, and storage medium.
Background
Under the current big data background, each part of the large information system gradually adopts a structured and easily-expanded assembly mode based on functions, and distributed software deployment is beneficial to software development and maintenance and is widely used in the computer fields of communication fields, big data development, artificial intelligence and the like.
The data distribution method has great influence on the data transmission of distributed software deployment. In the traditional method, point-to-point based on UDP and TCP/IP is a common data communication protocol, and is an underlying protocol in link communication. The point-to-point communication method is widely applied, but cannot achieve both transmission efficiency and reliability, and is often designed into complex packages for stable transmission, so that secondary development is not facilitated. Therefore, mature data transmission methods based on UDP and TCP/IP are attracting attention. Such as Client-server (C/S) architecture, can simultaneously meet the communication requirements of multiple clients and unified servers. The communication mode of the C/S structure is a request-response mode, is suitable for a communication framework of data centralization, such as a database, and the like, but has low efficiency and delay for the application mode of a plurality of information nodes. In the "publish-subscribe" (P/S) mode, information is only transferred between the publisher and subscriber, which does not have C/S centralization features, but there is still a problem in that the subscriber of data receives valid data and, at the same time, the subscriber processing burden is not considered, reducing the software running efficiency and causing data accumulation, so that real-time data processing service cannot be achieved. At this point, the distribution, although completing the data transmission, loses the overall operating efficiency of the distributed software.
Disclosure of Invention
The invention aims at overcoming the defects of the prior art, providing the name of the invention, dynamically planning data division based on the working states of different node processing software to obtain high-efficiency data distribution, improving the transmission efficiency, ensuring the transmission instantaneity and optimizing the processing performance of the sub-nodes; further, the running state of the child node is separated from the working state recorded by the central node, the software structure is clear, and frequent switching of the distribution caused by different state changes is avoided; and extracting data basic characteristics at the distribution node as a data dividing rule to avoid redundant data transmission.
The aim of the invention is achieved by the following technical scheme:
a data distribution method, comprising the steps of:
receiving original data and extracting basic characteristics corresponding to the original data;
matching the basic features with a basic feature library, and if the matching is successful, adding the original data into a corresponding cache queue of a node to which the matched basic feature library belongs; otherwise, adding the basic features into a basic feature library of the corresponding child node according to a preset configuration rule;
and after the data meets the distribution requirement, distributing the cache queue to the corresponding processing board.
Further, the matching specifically includes distance measurement, similarity is calculated in a threshold preset by a basic feature library, and a child node closest to the basic feature is searched.
Further, when data is distributed, a supervision decision is made on the data distribution state.
Further, the supervision decision comprises an operation state and working state supervision decision of each node.
Further, the operating state and working state supervision decision comprises the following steps:
receiving and reporting an operation state;
classifying the running states, including an idle processing state, a normal processing state and a busy processing state;
and executing running state conversion on the nodes in the idle processing state and the busy processing state, so that the nodes in the idle processing state and the busy processing state are converted into the nodes in the normal processing state.
Further, the classifying the running state specifically includes classifying the running state according to the current CPU, the memory usage, the number of input data and the number of caches.
Further, the operation state transition specifically includes:
if the node in the idle processing state has no data deletion or feature deletion, the basic features transferred by other nodes can be inserted; if data deletion or feature deletion exists, the basic features transferred by other nodes are not received, so that the number of the data deletion is reduced or the deleted basic features are retrieved;
if the node in the normal processing state does not have available idle processing state nodes and the node in the normal processing state does not have data deletion or feature deletion, the basic features transferred by other nodes can be inserted;
if the characteristic insertion of other nodes exists, returning the basic characteristic which does not belong to the node, and if the characteristic insertion of other nodes does not exist, transferring the basic characteristic to the node in the idle processing state or the node in the normal processing state; if there is no node capable of receiving the basic feature, data deletion is performed.
Further, if any node does not report the running state within the preset time, the basic characteristics of the node are transferred to other nodes in the idle processing state or nodes in the normal processing state.
In another aspect, the present application provides a computer device comprising a processor and a memory, the memory having stored therein a computer program that is loaded and executed by the processor to implement any one of the data distribution methods described above.
In another aspect, the present application provides a computer readable storage medium having stored therein a computer program that is loaded and executed by a processor to implement any one of the data distribution methods described above.
The invention has the beneficial effects that:
(1) The invention divides data by using the extracted basic characteristics, solves the data redundancy of the traditional distribution method, ensures that the child nodes process data in different ranges, and ensures that the data division is clear and reliable; the state decision method is put forward by utilizing the state feedback of the child node, the running state of the node is monitored, and the data distribution strategy can be dynamically adjusted, so that the problem that the traditional method only pays attention to data transmission and does not consider the running pressure of software is solved, and the running capacity of the child node is in an effective processing range; the data distribution method and the state decision method cooperatively operate, so that the data transmission efficiency is improved, and the operation efficiency of the whole distributed system is improved.
(2) Compared with the traditional bottom layer transmission method (UDP, TCP/IP), the invention has complex development, does not consider the bottom layer communication protocol, and realizes multipoint communication on the basis.
(3) Compared with a point-to-point transmission method, a Client-server (C/S), a secondary development method such as 'publish-subscribe' (P/S) and the like, the method only pays attention to data transmission without considering software pressure, and the method divides data by combining with the running state of the child node, so that high-efficiency transmission is realized.
(4) Compared with the traditional method that the software blocking cannot be predicted so that the system has time delay, the method further enables the software to efficiently process the data through data division, and the real-time performance of the whole system is ensured.
Drawings
Fig. 1 is a flow chart of data distribution steps of a data distribution method according to an embodiment of the present invention;
fig. 2 is a flow chart of a state supervision decision step of a data distribution method according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a software framework of a data distribution method according to an embodiment of the present invention.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
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.
In order to distribute data of a distributed system when the data volume is large, the data distribution method provided in this embodiment mainly includes two parts: data distribution management and state supervision decision-making. The data distribution management is responsible for creating a basic feature library, adding new features and completing data distribution; the state supervision decision is responsible for adjusting the base feature library based on the child node state.
Fig. 3 is a schematic diagram of a software framework of a data distribution method according to this embodiment. The data distribution system specifically comprises a data distribution center node and N data child nodes. The data distribution center node obtains the original data through the links and distributes the data to the N child nodes through the links. When receiving data distributed by the data distribution center node, the child nodes also return the states of the respective nodes, the state supervision and decision component of the data distribution center node receives the node states and adjusts the basic characteristics of each node according to the state information of each child node, so that dynamic planning of the data is realized, and the data distribution process is influenced.
As shown in fig. 1, the flow chart of the data distribution step of the data distribution method provided in this embodiment specifically includes the following steps:
step one: and receiving the original data x and extracting the corresponding basic characteristics of the original data. The input data x is extracted with the corresponding basic feature y, and the extraction mode of the basic feature is not limited here. In one particular embodiment, for pulse data, information such as frequency, PRI, etc. may be extracted as a fundamental feature.
Step two: judging a basic feature library to which the basic feature y belongs, namely matching the basic feature y with each node feature library, if the matching is successful, obtaining a node to which the original data x belongs, and adding the node into a corresponding cache queue; otherwise, adding the basic feature y into the corresponding feature library according to the child node feature range set by the configuration rule. The configuration rule is a basic feature range to be processed by each node.
In a specific embodiment, the matching method of the basic feature y and the basic feature library is distance measurement, and within the threshold thre, the sub-node most similar to the basic feature y is found, and the similarity calculation method is as follows.
Where simi is the similarity and t represents the features stored in the feature library.
Step three: after the data meets the distribution requirement, the data meeting the requirement is issued, and the cache queue is distributed to the corresponding processing board. If the data does not reach the distribution condition, the data is still waiting to be distributed in the cache queue.
In one embodiment, the data distribution state is also supervised and decided upon when the data distribution is performed. The state supervision decisions include running state and working state supervision decisions.
Fig. 2 is a flow chart of a state supervision decision step of a data distribution method according to an embodiment.
The state decision flow is specifically as follows:
and step one, receiving the running state reported by each child node.
And secondly, classifying the received operation states of the child nodes.
In a specific embodiment, the running state is divided into an idle processing state, a normal operation state, and a processing busy state. The idle processing state indicates that the current processing capability of the node has a great margin, and the input data is less and can receive new data. The normal working state indicates that the node can process the input data, has no data accumulation, has moderate input data and can properly insert the data. The busy state is processed to indicate that the node has more current cache data, cannot process the data in time, needs to divide the input data again, and needs to reduce the input data. In this embodiment, a status identifier is added to each status, the identifier of the idle processing status is run_free, the identifier of the NORMAL working status is run_normal, and the identifier of the BUSY processing status is run_busy.
The running state of the node is judged by the CPU, the memory utilization rate, the input data number, the cache number and the like of the current program. When in RUN BUSY state, the input to this node needs to be processed. The specific operation is selected according to the working state of the child node recorded by the central node. If the running state is not reported for a long time, the data distribution center node considers that the corresponding child node does not work, namely is in a 'dead state'.
The data distribution center node may also record the working states of the child nodes, where in a specific embodiment, the working states include a default state, a feature delete state, an insert state, and a data delete state. The default state indicates that the node only processes data divided by the configuration file in normal operation, and the data is not deleted, and the node is in an initial state and works normally; the feature deletion state indicates that the sub-node basic feature library deletes the configured basic features, and the basic features are deleted; the insertion state indicates that the child node inserts the basic characteristics of the configuration of other nodes, and the basic characteristics belonging to other nodes are inserted; the data deletion state means that only a certain amount of data is processed, other data is deleted, one beat of data cannot be processed completely, and redundant data is deleted.
For different operation states of the child nodes, different processing measures are adopted, including basic feature transfer (deletion and insertion), data deletion, basic feature restoration (deletion and insertion) and data restoration (not deletion). And when the basic feature operation is carried out, if the basic feature operation has the idle node and the normal node at the same time, the idle node is preferentially used. And when the idle node does not exist, the normal node is used for operation.
In a specific embodiment, the following processing measures are taken for the child nodes in different operation states:
for the nodes in the idle processing state, if no data is deleted or characteristics are deleted, basic characteristics transferred by other nodes can be inserted; if the data is deleted or the characteristics are deleted, the basic characteristics transferred by other nodes are not received, and the number of the data deletion is reduced or the deleted basic characteristics are retrieved.
For the node in the normal processing state, if there is no available node in the idle processing state and the node in the normal processing state has no data deletion or feature deletion, the basic feature transferred by other nodes can be inserted.
For the node in the busy processing state, if the feature insertion of other nodes exists, returning to the basic feature not belonging to the node, and if the feature insertion of other nodes does not exist, transferring the basic feature to the node in the idle processing state or the node in the normal processing state; if there is no node capable of receiving the basic feature, data deletion is performed.
According to the condition after each treatment, changing the working state recorded by the central node: if the child node has data deletion, entering a data deletion state; if the self characteristics are deleted, judging that the working state is a characteristic deletion state; if other node basic characteristics are inserted, the working state is changed into an insertion state; none exist as a default operating state. If the child node with dead running state occurs, the basic characteristics of the child node are transferred to other idle or normal child nodes.
According to the data distribution method provided by the embodiment, the extracted basic characteristics are utilized to divide data, so that the data redundancy of the traditional distribution method is solved, the child nodes process data in different ranges, and the data division is ensured to be clear and reliable; the state decision method is put forward by utilizing the state feedback of the child node, the running state of the node is monitored, and the data distribution strategy can be dynamically adjusted, so that the problem that the traditional method only pays attention to data transmission and does not consider the running pressure of software is solved, and the running capacity of the child node is in an effective processing range; the data distribution method and the state decision method cooperatively operate, so that the data transmission efficiency is improved, and the operation efficiency of the whole distributed system is improved.
Compared with the traditional bottom layer transmission method (UDP, TCP/IP), the data distribution method provided by the embodiment is complex to develop, and does not consider a bottom layer communication protocol, but realizes multipoint communication on the basis.
Compared with a point-to-point transmission method, a Client-server (C/S), a secondary development method such as release-subscription (P/S) and the like, the data distribution method provided by the embodiment only pays attention to data transmission without considering software pressure, and the method is combined with the operation state of the child node to divide the data, so that efficient transmission is realized.
Compared with the traditional method that software blocking cannot be predicted to cause delay of a system, the data distribution method provided by the embodiment further enables software to efficiently process data through data division, and ensures real-time performance of the whole system.
Example 2
The preferred embodiment provides a computer device, which can implement the steps in any embodiment of a data distribution method provided in the embodiment of the present application, so that the beneficial effects of the data distribution method provided in the embodiment of the present application can be implemented, and detailed descriptions of the foregoing embodiments are omitted herein.
Example 3
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, an embodiment of the present invention provides a storage medium having stored therein a plurality of instructions capable of being loaded by a processor to perform the steps of any one of the embodiments of a data distribution method provided by the embodiment of the present invention.
Wherein the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
The steps in any one of the data distribution method embodiments provided by the embodiment of the present invention may be executed by the instructions stored in the storage medium, so that the beneficial effects that any one of the data distribution methods provided by the embodiment of the present invention may be achieved, which are detailed in the previous embodiments and are not described herein.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. A data distribution method, comprising the steps of:
receiving original data and extracting basic characteristics corresponding to the original data;
matching the basic features with a basic feature library, and if the matching is successful, adding the original data into a corresponding cache queue of a node to which the matched basic feature library belongs; otherwise, adding the basic features into a basic feature library of the corresponding child node according to a preset configuration rule;
after the data meets the distribution requirement, the cache queue is distributed to a corresponding processing board;
when data is distributed, performing supervision decision on the data distribution state, wherein the supervision decision comprises supervision decision on the running state and the working state of each node;
the operating state and working state supervision decision comprises the following steps:
receiving and reporting an operation state;
classifying the running states, including an idle processing state, a normal processing state and a busy processing state;
and executing running state conversion on the nodes in the idle processing state and the busy processing state, so that the nodes in the idle processing state and the busy processing state are converted into the nodes in the normal processing state.
2. The data distribution method according to claim 1, wherein the matching specifically includes a distance measurement, a similarity is calculated within a threshold preset in a basic feature library, and a child node closest to the basic feature is found.
3. The data distribution method according to claim 1, wherein classifying the operation state specifically includes classifying the operation state according to a current CPU, a memory usage rate, a number of input data, and a number of caches.
4. The data distribution method according to claim 1, wherein the operation state transition specifically includes:
if the node in the idle processing state has no data deletion or feature deletion, the basic features transferred by other nodes can be inserted; if data deletion or feature deletion exists, the basic features transferred by other nodes are not received, so that the number of the data deletion is reduced or the deleted basic features are retrieved;
if the node in the normal processing state does not have available idle processing state nodes and the node in the normal processing state does not have data deletion or feature deletion, the basic features transferred by other nodes can be inserted;
if the characteristic insertion of other nodes exists, returning the basic characteristic which does not belong to the node, and if the characteristic insertion of other nodes does not exist, transferring the basic characteristic to the node in the idle processing state or the node in the normal processing state; if there is no node capable of receiving the basic feature, data deletion is performed.
5. The data distribution method according to claim 1, wherein if any node does not report the running state within a preset time, the basic feature of the node is transferred to the node in the other idle processing state or the node in the normal processing state.
6. A computer device comprising a processor and a memory, wherein the memory has stored therein a computer program that is loaded and executed by the processor to implement a data distribution method according to any of claims 1 to 5.
7. A computer readable storage medium, characterized in that the storage medium has stored therein a computer program, which is loaded and executed by a processor to implement a data distribution method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111025736.0A CN113919412B (en) | 2021-09-02 | 2021-09-02 | Data distribution method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111025736.0A CN113919412B (en) | 2021-09-02 | 2021-09-02 | Data distribution method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113919412A CN113919412A (en) | 2022-01-11 |
| CN113919412B true CN113919412B (en) | 2023-07-25 |
Family
ID=79233798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111025736.0A Active CN113919412B (en) | 2021-09-02 | 2021-09-02 | Data distribution method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113919412B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102843420A (en) * | 2012-07-02 | 2012-12-26 | 上海交通大学 | Fuzzy division based social network data distribution system |
| CN104184819A (en) * | 2014-08-29 | 2014-12-03 | 城云科技（杭州）有限公司 | Multi-hierarchy load balancing cloud resource monitoring method |
| CN105975345A (en) * | 2016-05-20 | 2016-09-28 | 江苏得得空间信息科技有限公司 | Video frame data dynamic equilibrium memory management method based on distributed memory |
| US9602617B1 (en) * | 2015-12-16 | 2017-03-21 | International Business Machines Corporation | High performance and scalable telematics message dispatching |
| WO2018103315A1 (en) * | 2016-12-09 | 2018-06-14 | 上海壹账通金融科技有限公司 | Monitoring data processing method, apparatus, server and storage equipment |
| CN111274288A (en) * | 2020-01-17 | 2020-06-12 | 腾讯云计算（北京）有限责任公司 | Distributed retrieval method, device, system, computer equipment and storage medium |
| CN111813573A (en) * | 2020-06-29 | 2020-10-23 | 中国平安人寿保险股份有限公司 | Communication method of management platform and robot software and related equipment thereof |
| WO2021047664A1 (en) * | 2019-09-12 | 2021-03-18 | 华为技术有限公司 | Biometric feature recognition method and related device |
| CN112749012A (en) * | 2021-01-15 | 2021-05-04 | 北京智芯微电子科技有限公司 | Data processing method, device and system of terminal equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2020237195B2 (en) * | 2019-03-14 | 2023-06-22 | Yadong Li | Distributed system generating rule compiler engine apparatuses, methods, systems and media |
-
2021
- 2021-09-02 CN CN202111025736.0A patent/CN113919412B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102843420A (en) * | 2012-07-02 | 2012-12-26 | 上海交通大学 | Fuzzy division based social network data distribution system |
| CN104184819A (en) * | 2014-08-29 | 2014-12-03 | 城云科技（杭州）有限公司 | Multi-hierarchy load balancing cloud resource monitoring method |
| US9602617B1 (en) * | 2015-12-16 | 2017-03-21 | International Business Machines Corporation | High performance and scalable telematics message dispatching |
| CN105975345A (en) * | 2016-05-20 | 2016-09-28 | 江苏得得空间信息科技有限公司 | Video frame data dynamic equilibrium memory management method based on distributed memory |
| WO2018103315A1 (en) * | 2016-12-09 | 2018-06-14 | 上海壹账通金融科技有限公司 | Monitoring data processing method, apparatus, server and storage equipment |
| WO2021047664A1 (en) * | 2019-09-12 | 2021-03-18 | 华为技术有限公司 | Biometric feature recognition method and related device |
| CN111274288A (en) * | 2020-01-17 | 2020-06-12 | 腾讯云计算（北京）有限责任公司 | Distributed retrieval method, device, system, computer equipment and storage medium |
| WO2021143351A1 (en) * | 2020-01-17 | 2021-07-22 | 腾讯科技（深圳）有限公司 | Distributed retrieval method, apparatus and system, computer device, and storage medium |
| CN111813573A (en) * | 2020-06-29 | 2020-10-23 | 中国平安人寿保险股份有限公司 | Communication method of management platform and robot software and related equipment thereof |
| CN112749012A (en) * | 2021-01-15 | 2021-05-04 | 北京智芯微电子科技有限公司 | Data processing method, device and system of terminal equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| Optimal Cache Budget Distribution for Hierarchical ICN Networks;Montazeri等;《International Workshop on QoE management》;第1-8页 * |
| 面向分布式计算的光互连节点设计与实现;杨深圳;《中国优秀硕士学位论文全文数据库 信息科技辑》(第8期);第I139-176页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113919412A (en) | 2022-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7457835B2 (en) | Movement of data in a distributed database system to a storage location closest to a center of activity for the data | |
| US7418454B2 (en) | Data overlay, self-organized metadata overlay, and application level multicasting | |
| CN111522636B (en) | Application container adjusting method, application container adjusting system, computer readable medium and terminal device | |
| US9703610B2 (en) | Extensible centralized dynamic resource distribution in a clustered data grid | |
| CN105975345A (en) | Video frame data dynamic equilibrium memory management method based on distributed memory | |
| CN108280018B (en) | Method and system for analyzing and optimizing communication overhead efficiency of node workflow | |
| CN113919412B (en) | Data distribution method, device and storage medium | |
| US8930345B2 (en) | Query optimization in a parallel computer system to reduce network traffic | |
| Yujie et al. | An effective controller placement algorithm based on clustering in SDN | |
| WO2022016969A1 (en) | Data processing method and device | |
| Fang et al. | Design and evaluation of a pub/sub service in the cloud | |
| CN113791913B (en) | Task migration method of brain-like computer operating system | |
| CN113075995B (en) | Virtual machine energy-saving integration method, system and storage medium based on hybrid group intelligence | |
| CN113328890B (en) | Network communication model construction method based on distributed system | |
| Rasool et al. | Replica placement in multi-tier data grid | |
| CN114598662A (en) | Message queue cluster federal management system and method | |
| Wang et al. | Multi-Granularity Decomposition for Componentized Multimedia Applications based on Graph Clustering | |
| CN112995241B (en) | Service scheduling method and device | |
| CN110138670B (en) | Load migration method based on dynamic path | |
| CN112783673A (en) | Method and device for determining call chain, computer equipment and storage medium | |
| CN112003900A (en) | Method and system for realizing high service availability under high-load scene in distributed system | |
| CN113630330B (en) | Multi-controller load balancing method and system for software defined network | |
| CN108491167A (en) | A kind of quick random distribution storage method of industrial process floor data | |
| CN117289878B (en) | Method and device for creating volume, computer equipment and storage medium | |
| WO2023051537A1 (en) | Policy adjustment method, data transmission method, and system, server and storage medium |
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 |