WO2019052075A1 - 一种基于时延构建弹性现场的查询增强系统及方法 - Google Patents

一种基于时延构建弹性现场的查询增强系统及方法 Download PDF

Info

Publication number
WO2019052075A1
WO2019052075A1 PCT/CN2017/117698 CN2017117698W WO2019052075A1 WO 2019052075 A1 WO2019052075 A1 WO 2019052075A1 CN 2017117698 W CN2017117698 W CN 2017117698W WO 2019052075 A1 WO2019052075 A1 WO 2019052075A1
Authority
WO
WIPO (PCT)
Prior art keywords
query
identifier
lqnj
queried
network address
Prior art date
Application number
PCT/CN2017/117698
Other languages
English (en)
French (fr)
Inventor
王劲林
盛益强
程钢
叶晓舟
邓浩江
王玲芳
Original Assignee
中国科学院声学研究所
北京中科海力技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中国科学院声学研究所, 北京中科海力技术有限公司 filed Critical 中国科学院声学研究所
Priority to SG11202000879VA priority Critical patent/SG11202000879VA/en
Priority to KR1020207002421A priority patent/KR102367540B1/ko
Priority to US16/632,900 priority patent/US11386103B2/en
Priority to EP17925418.0A priority patent/EP3686757A4/en
Priority to AU2017431351A priority patent/AU2017431351B2/en
Priority to JP2020515243A priority patent/JP6992168B2/ja
Priority to RU2020102290A priority patent/RU2760243C2/ru
Publication of WO2019052075A1 publication Critical patent/WO2019052075A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2477—Temporal data queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/22—Indexing; Data structures therefor; Storage structures
    • G06F16/2228—Indexing structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2453—Query optimisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2453—Query optimisation
    • G06F16/24534—Query rewriting; Transformation
    • G06F16/24537—Query rewriting; Transformation of operators
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2471—Distributed queries

Definitions

  • the invention belongs to the technical field of network technology and network communication, and particularly relates to a query enhancement system and method for constructing an elastic field based on time delay.
  • distributed queries include: Range query, aggregate search, Skyline search, Top-k search, and the like.
  • Range search refers to searching for all resources whose single or multiple attribute values are within a certain continuous interval.
  • the location identifier can be obtained by the location-sensitive hash algorithm on the basis of Chord, and the space filling curve can be used.
  • SFC technology single attribute and multiple attributes mapping ; aggregate search refers to a set of resources, some attributes aggregate information, such as count, sum, max, average, etc.;
  • Skyline search refers to a given set S Select a subset, any point in the subset can not be controlled by other points in S.
  • the control relationship of any two points p to q means that p is better than q in at least one dimension and in other dimensions. p is not worse than q.
  • the resolution system of mapping between name and address is an indispensable link in data transmission in the information center network (ICN), and its performance directly affects the overall performance of the information center network (ICN).
  • ICN information center network
  • each entity in the network obtains a location-independent self-authenticated entity unique identifier (EUID) as the name, through the EUID and the network address (NA) Dynamic binding to enable communication between entities in the information center network (ICN).
  • EUID location-independent self-authenticated entity unique identifier
  • NA network address
  • the main function of name resolution is to establish and maintain the mapping relationship between the content name and the network address published by the content provider, and then to find the appropriate content provider and its network address by searching the content name.
  • the prior art has the following problems:
  • the response time of the query is generally related to the node size, the size of the query area, and the number of resource attributes being queried (ie, the spatial dimension), but cannot be returned within a fixed time delay. search result.
  • the object of the present invention is to solve the above problems in the existing query enhancement system and method.
  • the present invention provides a query-enhanced system based on time delay to construct an elastic field, which effectively solves the problem of distributed organization and query, especially the information center.
  • the application scenario with a given low latency requirement is prioritized, and the near-far and near-distributed queries according to the location relationship are implemented.
  • the present invention provides a query enhancement system for constructing an elastic field based on time delay, comprising: logically dividing a network node to obtain a group of containers composed of a plurality of containers; wherein the plurality of containers have a nested relationship, that is, a plurality of containers constitute a group of containers, and each of the containers further includes: a management node for node organization, neighbor maintenance and query service in the container; wherein the logical division refers to A given container rule re-segmentes a set of physical nodes to form a logical node set, so that nodes not in the same physical scope can also form a neighbor relationship; the node organization refers to structural management of nodes in the container to form A logical topology; the neighbor maintenance refers to maintaining a direct connection state in the logical topology; the query service refers to retrieving the database when the request is received to return the requested content.
  • the query enhancement system for constructing an elastic field based on the delay includes: logically dividing the network node based on the delay indicator set ⁇ Ti ⁇ , and each delay indicator Ti corresponds to a Ci-level container with no overlapping full coverage.
  • the Ci-class containers have a nested relationship, that is, the plurality of Ci-class containers constitute a Ci+1-class container; wherein Ti ⁇ Ti+1, 1 ⁇ i ⁇ I-1, I is the number of layers of the nested container ;Ti is the actual query delay indicator.
  • the management topology of the query enhancement system based on the delay construction elastic field is a tree structure, and the root node is a management node of a CI-level container; the local query node accessed in any query request is recorded as LQNj, and The Ci-level container containing the local query node LQNj and the neighbors form an elastic field area for satisfying the requirement that the delay indicator set ⁇ Ti ⁇ is smaller than any given time delay upper limit Ts.
  • the request for querying that the delay indicator set ⁇ Ti ⁇ is smaller than any given time delay upper limit Ts specifically includes:
  • the present invention also discloses a query enhancement method for constructing an elastic field based on time delay, which comprises: performing network-node non-intersection full coverage logic division on a network node, a set of containers consisting of a plurality of containers, the plurality of containers having a nested relationship, respectively performing a query flow without a given low latency requirement and a near query process requiring a given low latency requirement; wherein
  • the query process without the given low latency requirement is implemented by using an existing query technology
  • the query process of the given low latency requirement uses the distributed nearest query method to perform the near query, so that the actual query delay index Ti is smaller than the requirement of a certain delay upper limit Ts. Its specific includes:
  • Step 1) When Ti ⁇ Ts, a local query node LQNj receives a query request for a given low latency requirement for an entity unique identifier ID, where Ti is the actual query delay indicator, and Ts is Upper limit of delay;
  • Step 4 for any satisfaction of 1 ⁇ i ⁇ I-1, check whether Ti ⁇ Ts ⁇ Ti + 1 is satisfied: if Ti ⁇ Ts ⁇ Ti +1 is satisfied, then proceed to the next step, if Ti ⁇ Ts ⁇ Ti+1, then jump to step 7);
  • Step 5 when Ti ⁇ Ts ⁇ Ti+1, forward the query request to the query node of the Ci-class container containing LQNj, denoted as Cik, and perform preliminary query in the Cik and its neighbor list ⁇ Cim ⁇ : If the network address corresponding to the identifier is queried, the process proceeds to the next step; if the network address corresponding to the identifier is not queried, the query fails to be returned;
  • Step 6 querying in the Cik and its neighbor list ⁇ Cim ⁇ ; if the network address corresponding to the identifier is queried, the query result is directly returned, and if the network address corresponding to the identifier is not queried, return Query failed;
  • Step 7 performing a preliminary query in the CI-level container containing LQNj; if the network address corresponding to the identifier is queried, proceed to the next step; if the network address corresponding to the identifier is not queried, jump to Step 9);
  • Step 8 in the CI-level container containing LQNj query; if the network address corresponding to the identifier is queried, the query result is directly returned; if the network address corresponding to the identifier is not queried, then the next step is performed. ;
  • Step 9) query the neighbor list ⁇ CIm ⁇ of the CI-level container containing LQNj by inter-domain exchange; if the network address corresponding to the identifier is queried in a CI-level container, record it as CIp, and go to the next Step; if the network address corresponding to the identifier is not queried, the query fails to be returned;
  • Step 10 forwarding the query request to the CIp, and performing a query in the CIp; if the network address corresponding to the identifier is queried, directly returning the query result; if the network address corresponding to the identifier is not queried, returning Query failed;
  • the query is performed in the LQNj receiving the query request, the C1 level container containing the LQNj, and the local hash table (HT) in the neighbor;
  • the query is performed in the Bloom filter BF in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • step 6 the query is performed in the distributed hash table DHT in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • a preliminary query is performed in the Bloom filter BF in the CI-class container containing LQNj;
  • the query is performed in a distributed hash table DHT in a CI-level container containing LQNj;
  • the query is performed in the Bloom filter BF in the neighbor list ⁇ CIm ⁇ of the CI-level container containing LQNj;
  • the query is made in a distributed hash table DHT in the CIp.
  • the neighbor query process with a given low latency requirement may degrade the C1k neighbor list ⁇ C1m ⁇ into a non-neighbor C1 level container, and the specific query process includes:
  • Step 1) When Ti ⁇ Ts, a local query node LQNj receives a query request for a given low latency requirement for an entity unique identifier ID, where Ti is the actual query delay indicator, and Ts is Time Extended ceiling
  • Step 4 for any satisfaction of 1 ⁇ i ⁇ I-1, check whether Ti ⁇ Ts ⁇ Ti + 1 is satisfied: if Ti ⁇ Ts ⁇ Ti +1 is satisfied, then proceed to the next step, if Ti ⁇ Ts ⁇ Ti+1, then jump to step 7);
  • Step 5 when Ti ⁇ Ts ⁇ Ti+1, forward the query request to the query node of the Ci-class container containing LQNj, denoted as Cik, and perform preliminary query in the Cik and its neighbor list ⁇ Cim ⁇ : If the network address corresponding to the identifier is queried, the process proceeds to the next step; if the network address corresponding to the identifier is not queried, the query fails to be returned;
  • Step 6 querying in the Cik and its neighbor list ⁇ Cim ⁇ ; if the network address corresponding to the identifier is queried, the query result is directly returned, and if the network address corresponding to the identifier is not queried, the query fails to be returned. ;
  • Step 7 performing a preliminary query in the CI-level container containing LQNj; if the network address corresponding to the identifier is queried, proceed to the next step; if the network address corresponding to the identifier is not queried, jump to Step 9);
  • Step 8 in the CI-level container containing LQNj query; if the network address corresponding to the identifier is queried, the query result is directly returned; if the network address corresponding to the identifier is not queried, then the next step is performed. ;
  • the query is performed in the Bloom filter BF in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • step 6 the query is performed in the distributed hash table DHT in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • a preliminary query is performed in the Bloom filter BF in the CI-class container containing LQNj;
  • the query is performed in a distributed hash table DHT in a CI-level container containing LQNj;
  • the invention has the advantages that the invention is applicable to various delay sensitive applications including low delay and high reliability.
  • a query enhancement system and method for constructing an elastic field based on time delay is disclosed, which satisfies the request processing requirement for returning query results within a given low time delay.
  • FIG. 1 is a schematic diagram of a framework of a query-enhanced system for constructing an elastic field based on time delay according to the present invention
  • the present invention provides a query enhancement system for constructing an elastic field based on time delay, comprising: logically dividing a network node to obtain a group of containers consisting of several containers; wherein, between the plurality of containers Having a nested relationship, that is, a plurality of containers constitute a group of containers, and each of the containers further includes: a management node for node organization, neighbor maintenance and query service in the container; wherein the logical division refers to The physical node set is re-segmented according to a given container rule to form a logical node set, so that nodes not in the same physical scope can also form a neighbor relationship; the node organization refers to structural management of nodes in the container, Forming a logical topology; the neighbor maintenance refers to maintaining a direct connection state in the logical topology; the query service refers to retrieving the database when the request is received, to return the requested content.
  • the query enhancement system for constructing an elastic field based on the delay includes: a delay index set ⁇ Ti ⁇ ; logically dividing the network node, each delay index Ti corresponding to a layer of Ci-level containers without overlapping full coverage,
  • the Ci-class containers have a nested relationship, that is, the plurality of Ci-class containers constitute a Ci+1-class container; wherein Ti ⁇ Ti+1, 1 ⁇ i ⁇ I-1, I is the number of layers of the nested container ;Ti is the actual query delay indicator.
  • the management topology of the query enhancement system based on the delay construction elastic field is a tree structure, the root node is a management node of the CI level container; the local query node requested to access in any query is recorded as LQNj, and the local The Ci-level container of the query node LQNj and its neighbors form an elastic field area for satisfying the requirement that the delay index ⁇ Ti ⁇ is smaller than any given time delay upper limit Ts.
  • the request for querying that the delay indicator set ⁇ Ti ⁇ is smaller than any given time delay upper limit Ts specifically includes:
  • the present invention also discloses a query enhancement method for constructing an elastic field based on time delay, which comprises: performing network-node non-intersection full coverage logic division on a network node, a set of containers consisting of a plurality of containers, the plurality of containers having a nested relationship, respectively performing a query flow without a given low latency requirement and a near query process requiring a given low latency requirement; wherein
  • the query process without the given low latency requirement is implemented by using an existing query technology
  • the query process of the given low latency requirement uses the distributed proximity query method to perform the near query, so that the actual query delay index Ti is smaller than the requirement of a certain delay upper limit Ts, which specifically includes:
  • Step 1) When Ti ⁇ Ts, a local query node LQNj receives a query request for a given low latency requirement for an entity unique identifier ID, where Ti is the actual query delay indicator, and Ts is Upper limit of delay;
  • Step 4 for any satisfaction of 1 ⁇ i ⁇ I-1, check whether Ti ⁇ Ts ⁇ Ti + 1 is satisfied: if Ti ⁇ Ts ⁇ Ti +1 is satisfied, then proceed to the next step, if Ti ⁇ Ts ⁇ Ti+1, then jump to step 7);
  • Step 5 when Ti ⁇ Ts ⁇ Ti+1, forward the query request to the query node of the Ci-class container containing LQNj, denoted as Cik, and perform preliminary query in the Cik and its neighbor list ⁇ Cim ⁇ : If the network address corresponding to the identifier is queried, the process proceeds to the next step; if the network address corresponding to the identifier is not queried, the query fails to be returned;
  • Step 6 querying in the Cik and its neighbor list ⁇ Cim ⁇ ; if the network address corresponding to the identifier is queried, the query result is directly returned, and if the network address corresponding to the identifier is not queried, the query fails to be returned. ;
  • Step 7 performing a preliminary query in the CI-level container containing LQNj; if the network address corresponding to the identifier is queried, proceed to the next step; if the network address corresponding to the identifier is not queried, jump to Step 9);
  • Step 8 in the CI-level container containing LQNj query; if the network address corresponding to the identifier is queried, the query result is directly returned; if the network address corresponding to the identifier is not queried, then the next step is performed. ;
  • Step 9) query the neighbor list ⁇ CIm ⁇ of the CI-level container containing LQNj by inter-domain exchange; if the network address corresponding to the identifier is queried in a CI-level container, record it as CIp, and go to the next Step; if the network address corresponding to the identifier is not queried, the query fails to be returned;
  • Step 10 forwarding the query request to the CIp, and performing a query in the CIp; if the network address corresponding to the identifier is queried, directly returning the query result; if the network address corresponding to the identifier is not queried, returning Query failed;
  • the query is performed in the LQNj receiving the query request, the C1 level container containing the LQNj, and the local hash table (HT) in the neighbor;
  • the query is performed in the Bloom filter BF in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • step 6 the query is performed in the distributed hash table DHT in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • a preliminary query is performed in the Bloom filter BF in the CI-class container containing LQNj;
  • the query is performed in a distributed hash table DHT in a CI-level container containing LQNj;
  • the query is performed in the Bloom filter BF in the neighbor list ⁇ CIm ⁇ of the CI-level container containing LQNj;
  • the query is made in a distributed hash table DHT in the CIp.
  • the C1k neighbor list ⁇ C1m ⁇ may be degenerated into a non-neighbor C1 level container, and the specific query is performed.
  • the process includes:
  • Step 1) When Ti ⁇ Ts, a local query node LQNj receives a query request for a given low latency requirement for an entity unique identifier ID, where Ti is the current actual query delay indicator, Ts The upper limit of time delay;
  • Step 4 for any satisfaction of 1 ⁇ i ⁇ I-1, check whether Ti ⁇ Ts ⁇ Ti + 1 is satisfied: if Ti ⁇ Ts ⁇ Ti +1 is satisfied, then proceed to the next step, if Ti ⁇ Ts ⁇ Ti+1, then jump to step 7);
  • Step 5 when Ti ⁇ Ts ⁇ Ti+1, forward the query request to the query node of the Ci-class container containing LQNj, denoted as Cik, and perform preliminary query in the Cik and its neighbor list ⁇ Cim ⁇ : If the network address corresponding to the identifier is queried, the process proceeds to the next step; if the network address corresponding to the identifier is not queried, the query fails to be returned;
  • Step 6 querying in the Cik and its neighbor list ⁇ Cim ⁇ ; if the network address corresponding to the identifier is queried, the query result is directly returned, and if the network address corresponding to the identifier is not queried, the query fails to be returned. ;
  • Step 7 performing a preliminary query in the CI-level container containing LQNj; if the network address corresponding to the identifier is queried, proceed to the next step; if the network address corresponding to the identifier is not queried, jump to Step 9);
  • Step 8 in the CI-level container containing LQNj query; if the network address corresponding to the identifier is queried, the query result is directly returned; if the network address corresponding to the identifier is not queried, then the next step is performed. ;
  • the query is performed in the Bloom filter BF in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • step 6 the query is performed in the distributed hash table DHT in the Cik and its neighbor list ⁇ Cim ⁇ ;
  • a preliminary query is performed in the Bloom filter BF in the CI-class container containing LQNj;
  • the query is performed in a distributed hash table DHT in a CI-level container containing LQNj;

Abstract

本发明涉及一种基于时延构建弹性现场的查询增强系统，包括：对网络节点进行逻辑划分得到由若干容器组成的一组容器；该若干容器间具有嵌套关系，若干容器构成一组容器，每个该容器包括：一管理节点，用于该容器内的节点组织、邻居维护与查询服务；还公开了一种基于时延构建弹性现场的查询增强方法，包括：对网络节点进行同层无交集全覆盖逻辑划分，得到由若干容器组成的一组容器，该若干容器间具有嵌套关系，分别执行无给定低时延要求的查询流程和给定低时延要求的就近查询流程；该无给定低时延要求的查询流程，采用现有查询技术；该给定低时延要求的查询流程，采用分布式就近查询方法进行就近查询，实际查询时延指标Ti小于某个时延上限Ts的要求。

Description

一种基于时延构建弹性现场的查询增强系统及方法
本申请要求名称为“一种基于时延构建弹性现场的查询增强系统及方法”、于2017年9月18日提交的中国专利申请号为No.201710841537.4的优先权，在此通过引用包括该件申请。
技术领域
本发明属于网络技术和网络通信技术领域，具体涉及一种基于时延构建弹性现场的查询增强系统及方法。
背景技术
在现有技术中，分布式查询(query)包括：区间搜索(Range query)、聚合搜索、Skyline搜索、Top-k搜索等。其中，区间搜索(Range query)是指搜索单一或多个属性值处于某个连续区间内的所有资源，比如可以在Chord基础上通过位置敏感的哈希算法来获得属性标识，可以采用空间填充曲线SFC技术单一属性与多个属性间的映射；聚合搜索是指对一组资源某些属性聚合信息，如count、sum、max、average等的查询；Skyline搜索是指从一个给定的集合S中选择一个子集，该子集中的任一点都不能被S中的其它点所控制，其中的任意两点p对q的控制关系是指p至少在某一维度上好于q而且在其它维度上p都不比q差。
作为分布式查询的一个典型应用场景，名字与地址之间映射关系的解析系统是信息中心网络(ICN)中数据传输中不可缺少的环节，其性能直接影响到信息中心网络(ICN)的整体性能。通过信息中心网络(ICN)的命名机制，网络中的每个实体都获得一个与位置无关的具有自验证特征的实体唯一标识符(EUID)作为名字，通过对EUID与所在网络地址(NA)的动态绑定，实现信息中心网络(ICN)中实体间的通信。名字解析的主要功能，是用来建立并维护内容提供者所发布的内容名字与网络地址之间的映射关系，进而可以通过对内容名字的检索，找到合适的内容提供者及其网络地址。但是，现有技术存在以下问题：
1)尽管根据网络特点通过容器或者结构化技术将内容空间进行了嵌套和分层处理，然而当前的划分方法与系统的响应时间和应用需求无关，而结构上的 服务性能无关性显然无法直接满足时延的需求；
2)在对移动性和安全性有较高要求的环境下，无法提供一种根据响应时间需求或者性能要求的弹性可伸缩查询方法，无法在提升资源利用率的同时保障查找效率和精度。
另外，在现有的分布式查询方法中，查询的响应时间一般都与节点规模、查询区域大小、被查询的资源属性个数(即空间维度)相关，但是，无法在固定的时延内返回查询结果。为了解决上述问题，有必要提议了一种基于时延构建弹性现场的查询增强系统及方法，以满足一些应用场景下的给定低时延内返回查询结果的请求处理需求。
发明内容
本发明的目的在于，为了解决现有的查询增强系统和方法存在上述问题，本发明提供了一种基于时延构建弹性现场的查询增强系统，有效解决分布式组织与查询问题，特别是信息中心网络ICN中对有给定低时延要求的应用场景进行优先处理，实现按照位置关系由近及远的分布式就近查询。
为了实现上述目的，本发明提供了一种基于时延构建弹性现场的查询增强系统，其包括：对网络节点进行逻辑划分得到由若干容器组成的一组容器；其中，所述若干容器之间具有嵌套关系，即若干容器构成一组容器，且每个所述容器进一步包括：一个管理节点，用于所述容器内的节点组织、邻居维护与查询服务；其中，所述逻辑划分是指依据给定的容器规则对物理节点集合进行重新分割而形成逻辑节点集合，使不在同一个物理范围中的节点也可以形成邻居关系；所述节点组织是指对容器内的节点进行结构化管理，形成一个逻辑拓扑结构；所述邻居维护是指保持对逻辑拓扑结构中的直连状态；所述查询服务是指当收到请求时对数据库进行检索，以返回所请求的内容。
所述基于时延构建弹性现场的查询增强系统具体包括：基于时延指标集合{Ti}，对网络节点进行逻辑划分，每个时延指标Ti对应一层无交集全覆盖的Ci级容器，所述Ci级容器间具有嵌套关系，即多个所述Ci级容器构成一个Ci+1级容器；其中，Ti＜Ti+1，1≤i≤I-1，I为嵌套容器的层数；Ti为实际查询时延指标。
所述基于时延构建弹性现场的查询增强系统的管理拓扑为树形结构，根节点为CI级容器的管理节点；在任一查询请求接入的本地查询节点，记为LQNj，与 含有所述本地查询节点LQNj的Ci级容器，及其邻居之间形成一个弹性现场区域，用于满足查询所述时延指标集合{Ti}小于任意给定时延上限Ts的需求。
所述查询所述时延指标集合{Ti}小于任意给定时延上限Ts的需求具体包括：
a)当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；
b)当Ti≤Ts＜Ti+1时，在含有LQNj的Ci级容器及其邻居中进行查询；
c)当Ts≥TI，i＝I时，在含有LQNj的CI级容器中进行查询。
基于上述一种基于时延构建弹性现场的查询增强系统，本发明还公开了一种基于时延构建弹性现场的查询增强方法，包括：对网络节点进行同层无交集全覆盖逻辑划分，得到由若干容器组成的一组容器，所述若干容器之间具有嵌套关系，分别执行无给定低时延要求的查询流程和给定低时延要求的就近查询流程；其中，
所述无给定低时延要求的查询流程，采用现有查询技术来实现；
所述给定低时延要求的查询流程，采用分布式就近查询方法进行就近查询，使得实际查询时延指标Ti小于某个时延上限Ts的要求。其具体包括：
步骤1)、当Ti＜Ts时，某个本地查询节点LQNj接收到针对某个实体唯一标识符ID的给定低时延要求下的查询请求，其中，Ti为实际查询时延指标，Ts为时延上限；
步骤2)、当i＝1时，判断是否满足Ts＜T1：若Ts＜T1，则转至下一步骤；若Ts大于或等于T1，则跳转至步骤4)；
步骤3)、当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，返回查询失败；
步骤4)、对于任意满足1≤i≤I-1，检查是否满足Ti≤Ts＜Ti+1：若满足Ti≤Ts＜Ti+1，则转至下一步骤，若不满足Ti≤Ts＜Ti+1，则跳转至步骤7)；
步骤5)、当Ti≤Ts＜Ti+1时，将查询请求转发给含有LQNj的Ci级容器的查询节点，记为Cik，则在该Cik及其邻居列表{Cim}中进行初步查询：若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤6)、在该Cik及其邻居列表{Cim}中查询；若查询到标识符所对应的网络地址，则直接返回查询结果，若没有查询到标识符所对应的网络地址，则返回 查询失败；
步骤7)、在含有LQNj的CI级容器中进行初步查询；若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则跳转至步骤9)；
步骤8)、在含有LQNj的CI级容器中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则转至下一步骤；
步骤9)、通过域间交换查询含有LQNj的CI级容器的邻居列表{CIm}；若在某个CI级容器中查询到标识符所对应的网络地址，则记为CIp，并转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤10)、将查询请求转发到CIp，并在该CIp中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则返回查询失败；
优选地，所述步骤3)中，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中的本地哈希表(HT)中进行查询；
优选地，步骤5)中，在该Cik及其邻居列表{Cim}中的布隆滤波器BF中进行查询；
优选地，步骤6)中，在该Cik及其邻居列表{Cim}中的分布式哈希表DHT中进行查询；
优选地，步骤7)中，在含有LQNj的CI级容器中的布隆滤波器BF中进行初步查询；
优选地，步骤8)中，在含有LQNj的CI级容器中的分布式哈希表DHT中进行查询；
优选地，步骤9)中，在含有LQNj的CI级容器的邻居列表{CIm}中的布隆滤波器BF中进行查询；
优选地，在该CIp中的分布式哈希表DHT中进行查询。
在上述技术方案中，所述给定低时延要求的就近查询流程，为了节省维护代价，可以将C1k的邻居列表{C1m}退化为一个无邻居的C1级容器，其具体查询流程包括：
步骤1)、当Ti＜Ts时，某个本地查询节点LQNj接收到针对某个实体唯一标识符ID的给定低时延要求下的查询请求，其中，Ti为实际查询时延指标，Ts为时 延上限；
步骤2)、当i＝1时，判断是否满足Ts＜T1：若Ts＜T1，则转至下一步骤；若Ts大于或等于T1，则跳转至步骤4)；
步骤3)、当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，返回查询失败；
步骤4)、对于任意满足1≤i≤I-1，检查是否满足Ti≤Ts＜Ti+1：若满足Ti≤Ts＜Ti+1，则转至下一步骤，若不满足Ti≤Ts＜Ti+1，则跳转至步骤7)；
步骤5)、当Ti≤Ts＜Ti+1时，将查询请求转发给含有LQNj的Ci级容器的查询节点，记为Cik，则在该Cik及其邻居列表{Cim}中进行初步查询：若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤6)、在该Cik及其邻居列表{Cim}中查询；若查询到标识符所对应的网络地址，则直接返回查询结果，若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤7)、在含有LQNj的CI级容器中进行初步查询；若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则跳转至步骤9)；
步骤8)、在含有LQNj的CI级容器中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则转至下一步骤；
优选地，步骤5)中，在该Cik及其邻居列表{Cim}中的布隆滤波器BF中进行查询；
优选地，步骤6)中，在该Cik及其邻居列表{Cim}中的分布式哈希表DHT中进行查询；
优选地，步骤7)中，在含有LQNj的CI级容器中的布隆滤波器BF中进行初步查询；
优选地，步骤8)中，在含有LQNj的CI级容器中的分布式哈希表DHT中进行查询；
本发明的优点在于：本发明针对包括低时延、高可靠在内的各种时延敏感应 用，公开了一种基于时延构建弹性现场的查询增强系统及方法，满足了给定低时延内返回查询结果的请求处理需求。通过按照位置关系由近及远的分布式就近查询，并对低时延应用场景进行优先处理，可大幅缩短整体查询时间。
附图说明
图1是本发明的一种基于时延构建弹性现场的查询增强系统的框架示意图；
具体实施方式
如图1所示，本发明提供了一种基于时延构建弹性现场的查询增强系统，其包括：对网络节点进行逻辑划分得到由若干容器组成的一组容器；其中，所述若干容器之间具有嵌套关系，即若干容器构成一组容器，且每个所述容器进一步包括：一个管理节点，用于所述容器内的节点组织、邻居维护与查询服务；其中，所述逻辑划分是指依据给定的容器规则对物理节点集合进行重新分割而形成逻辑节点集合，使不在同一个物理范围中的节点也可以形成邻居关系；所述节点组织是指对容器内的节点进行结构化管理，形成一个逻辑拓扑结构；所述邻居维护是指保持对逻辑拓扑结构中的直连状态；所述查询服务是指当收到请求时对数据库进行检索，以返回所请求的内容。
所述基于时延构建弹性现场的查询增强系统具体包括：基于时延指标集合{Ti}；对网络节点进行逻辑划分，每个时延指标Ti对应一层无交集全覆盖的Ci级容器，所述Ci级容器间具有嵌套关系，即多个所述Ci级容器构成一个Ci+1级容器；其中，Ti＜Ti+1，1≤i≤I-1，I为嵌套容器的层数；Ti为实际查询时延指标。
所述基于时延构建弹性现场的查询增强系统的管理拓扑为树形结构，根节点为CI级容器的管理节点；在任一查询请求接入的本地查询节点，记为LQNj，与含有所述本地查询节点LQNj的Ci级容器，及其邻居之间形成一个弹性现场区域，用于满足查询所述时延指标{Ti}小于任意给定时延上限Ts的需求。
所述查询所述时延指标集合{Ti}小于任意给定时延上限Ts的需求具体包括：
a)当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；
b)当Ti≤Ts＜Ti+1时，在含有LQNj的Ci级容器及其邻居中进行查询；
c)当Ts≥TI，i＝I时，在含有LQNj的CI级容器中进行查询。
基于上述一种基于时延构建弹性现场的查询增强系统，本发明还公开了一种基于时延构建弹性现场的查询增强方法，包括：对网络节点进行同层无交集全覆盖逻辑划分，得到由若干容器组成的一组容器，所述若干容器之间具有嵌套关系，分别执行无给定低时延要求的查询流程和给定低时延要求的就近查询流程；其中，
所述无给定低时延要求的查询流程，采用现有查询技术来实现；
所述给定低时延要求的查询流程，采用分布式就近查询方法进行就近查询，使得实际查询时延指标Ti小于某个时延上限Ts的要求，其具体包括：
步骤1)、当Ti＜Ts时，某个本地查询节点LQNj接收到针对某个实体唯一标识符ID的给定低时延要求下的查询请求，其中，Ti为实际查询时延指标，Ts为时延上限；
步骤2)、当i＝1时，判断是否满足Ts＜T1：若Ts＜T1，则转至下一步骤；若Ts大于或等于T1，则跳转至步骤4)；
步骤3)、当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，返回查询失败；
步骤4)、对于任意满足1≤i≤I-1，检查是否满足Ti≤Ts＜Ti+1：若满足Ti≤Ts＜Ti+1，则转至下一步骤，若不满足Ti≤Ts＜Ti+1，则跳转至步骤7)；
步骤5)、当Ti≤Ts＜Ti+1时，将查询请求转发给含有LQNj的Ci级容器的查询节点，记为Cik，则在该Cik及其邻居列表{Cim}中进行初步查询：若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤6)、在该Cik及其邻居列表{Cim}中查询；若查询到标识符所对应的网络地址，则直接返回查询结果，若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤7)、在含有LQNj的CI级容器中进行初步查询；若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则跳转至步骤9)；
步骤8)、在含有LQNj的CI级容器中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则转至下一步骤；
步骤9)、通过域间交换查询含有LQNj的CI级容器的邻居列表{CIm}；若在某个CI级容器中查询到标识符所对应的网络地址，则记为CIp，并转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤10)、将查询请求转发到CIp，并在该CIp中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则返回查询失败；
优选地，所述步骤3)中，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中的本地哈希表(HT)中进行查询；
优选地，步骤5)中，在该Cik及其邻居列表{Cim}中的布隆滤波器BF中进行查询；
优选地，步骤6)中，在该Cik及其邻居列表{Cim}中的分布式哈希表DHT中进行查询；
优选地，步骤7)中，在含有LQNj的CI级容器中的布隆滤波器BF中进行初步查询；
优选地，步骤8)中，在含有LQNj的CI级容器中的分布式哈希表DHT中进行查询；
优选地，步骤9)中，在含有LQNj的CI级容器的邻居列表{CIm}中的布隆滤波器BF中进行查询；
优选地，在该CIp中的分布式哈希表DHT中进行查询。
在上述技术方案中，所述给定低时延要求的就近查询流程，为了节省维护代价，可以将C1k的邻居列表{C1m}退化为一个无邻居的C1级容器，其具体查询 流程包括：
步骤1)、当Ti＜Ts时，某个本地查询节点LQNj接收到针对某个实体唯一标识符ID的给定低时延要求下的查询请求，其中，Ti为当前实际查询时延指标，Ts为时延上限；
步骤2)、当i＝1时，判断是否满足Ts＜T1：若Ts＜T1，则转至下一步骤；若Ts大于或等于T1，则跳转至步骤4)；
步骤3)、当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，返回查询失败；
步骤4)、对于任意满足1≤i≤I-1，检查是否满足Ti≤Ts＜Ti+1：若满足Ti≤Ts＜Ti+1，则转至下一步骤，若不满足Ti≤Ts＜Ti+1，则跳转至步骤7)；
步骤5)、当Ti≤Ts＜Ti+1时，将查询请求转发给含有LQNj的Ci级容器的查询节点，记为Cik，则在该Cik及其邻居列表{Cim}中进行初步查询：若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤6)、在该Cik及其邻居列表{Cim}中查询；若查询到标识符所对应的网络地址，则直接返回查询结果，若没有查询到标识符所对应的网络地址，则返回查询失败；
步骤7)、在含有LQNj的CI级容器中进行初步查询；若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则跳转至步骤9)；
步骤8)、在含有LQNj的CI级容器中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则转至下一步骤；
优选地，步骤5)中，在该Cik及其邻居列表{Cim}中的布隆滤波器BF中进行查询；
优选地，步骤6)中，在该Cik及其邻居列表{Cim}中的分布式哈希表DHT中进行查询；
优选地，步骤7)中，在含有LQNj的CI级容器中的布隆滤波器BF中进行初步查询；
优选地，步骤8)中，在含有LQNj的CI级容器中的分布式哈希表DHT中进行查询；
最后所应说明的是，以上实施例仅用以说明本发明的技术方案而非限制。尽管参照实施例对本发明进行了详细说明，本领域的普通技术人员应当理解，对本发明的技术方案进行修改或者等同替换，都不脱离本发明技术方案的精神和范围，其均应涵盖在本发明的权利要求范围当中。

Claims (14)

  1. 一种基于时延构建弹性现场的查询增强系统，其特征在于，其包括：对网络节点进行逻辑划分得到由若干容器组成的一组容器；其中，所述若干容器之间具有嵌套关系，即若干容器构成一组容器，且每个所述容器进一步包括：一个管理节点，用于所述容器内的节点组织、邻居维护与查询服务。
  2. 根据权利要求1所述的基于时延构建弹性现场的查询增强系统，其特征在于，所述基于时延构建弹性现场的查询增强系统具体包括：基于时延指标集合{Ti}，对网络节点进行逻辑划分，每个时延指标Ti对应一层无交集全覆盖的Ci级容器，所述Ci级容器间具有嵌套关系，即多个所述Ci级容器构成一个Ci+1级容器；其中，Ti＜Ti+1，1≤i≤I-1，I为嵌套容器的层数；Ti为实际查询时延指标。
  3. 根据权利要求2所述的基于时延构建弹性现场的查询增强系统，其特征在于，基于时延构建弹性现场的查询增强系统的管理拓扑为树形结构，根节点为CI级容器的管理节点；在任一查询请求接入的本地查询节点，记为LQNj，与含有所述本地查询节点LQNj的Ci级容器，及其邻居之间形成一个弹性现场区域，用于满足查询所述时延指标{Ti}小于任意给定时延上限Ts的需求。
  4. 根据权利要求3所述的基于时延构建弹性现场的查询增强系统，其特征在于，所述查询所述时延指标{Ti}小于任意给定时延上限Ts的需求具体包括：
    a)当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；
    b)当Ti≤Ts＜Ti+1时，在含有LQNj的Ci级容器及其邻居中进行查询；
    c)当Ts≥TI，i＝I时，在含有LQNj的CI级容器中进行查询。
  5. 一种基于上述权利要求1-4中任一所述的基于时延构建弹性现场的查询增强系统的查询增强方法，包括：对网络节点进行同层无交集全覆盖逻辑划分，得到由若干容器组成的一组容器，所述若干容器之间具有嵌套关系，分别执行无给定低时延要求的查询流程和给定低时延要求的就近查询流程；其中，
    所述无给定低时延要求的查询流程，采用包括直接映射、聚合搜索、Skyline搜索、Top-k搜索在内的现有查询技术来实现查询，获得标识符所对应的网络地 址；
    所述给定低时延要求的查询流程，采用分布式就近查询方法进行就近查询，使得实际查询时延指标Ti小于某个时延上限Ts的要求。
  6. 根据权利要求5所述的查询增强方法，其特征在于，所述就近查询，实际查询时延指标Ti小于某个时延上限Ts的要求，其具体包括：
    步骤1)、当Ti＜Ts时，某个本地查询节点LQNj接收到针对某个实体唯一标识符ID的给定低时延要求下的查询请求，其中，Ti为实际查询时延指标，Ts为时延上限；
    步骤2)、当i＝1时，判断是否满足Ts＜T1：若Ts＜T1，则转至下一步骤；若Ts大于或等于T1，则跳转至步骤4)；
    步骤3)、当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，返回查询失败；
    步骤4)、对于任意满足1≤i≤I-1，检查是否满足Ti≤Ts＜Ti+1：若满足Ti≤Ts＜Ti+1，则转至下一步骤，若不满足Ti≤Ts＜Ti+1，则跳转至步骤7)；
    步骤5)、当Ti≤Ts＜Ti+1时，将查询请求转发给含有LQNj的Ci级容器的查询节点，记为Cik，则在该Cik及其邻居列表{Cim}中进行初步查询：若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
    步骤6)、在该Cik及其邻居列表{Cim}中查询；若查询到标识符所对应的网络地址，则直接返回查询结果，若没有查询到标识符所对应的网络地址，则返回查询失败；
    步骤7)、在含有LQNj的CI级容器中进行初步查询；若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则跳转至步骤9)；
    步骤8)、在含有LQNj的CI级容器中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则转至下一步骤；
    步骤9)、通过域间交换查询含有LQNj的CI级容器的邻居列表{CIm}；若在某个CI级容器中查询到标识符所对应的网络地址，则记为CIp，并转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；
    步骤10)、将查询请求转发到CIp，并在该CIp中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则返回查询失败。
  7. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，所述步骤3)中，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中的本地哈希表HT中进行查询。
  8. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，步骤5)中，在该Cik及其邻居列表{Cim}中的布隆滤波器BF中进行查询。
  9. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，步骤6)中，在该Cik及其邻居列表{Cim}中的分布式哈希表DHT中进行查询。
  10. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，步骤7)中，在含有LQNj的CI级容器中的布隆滤波器BF中进行初步查询。
  11. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，步骤8)中，在含有LQNj的CI级容器中的分布式哈希表DHT中进行查询。
  12. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，步骤9)中，在含有LQNj的CI级容器的邻居列表{CIm}中的布隆滤波器BF中进行查询。
  13. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，步骤10)中，在该CIp中的分布式哈希表DHT中进行查询。
  14. 根据权利要求5所述的基于时延构建弹性现场的查询增强方法，其特征在于，所述给定低时延要求的就近查询流程，将C1k的邻居列表{C1m}退化为一 个无邻居的C1级容器，其具体查询流程包括：
    步骤1)、当Ti＜Ts时，某个本地查询节点LQNj接收到针对某个实体唯一标识符ID的给定低时延要求下的查询请求，其中，Ti为实际查询时延指标，Ts为时延上限；
    步骤2)、当i＝1时，判断是否满足Ts＜T1：若Ts＜T1，则转至下一步骤；若Ts大于或等于T1，则跳转至步骤4)；
    步骤3)、当Ts＜T1，i＝1时，在接收到查询请求的LQNj、含有LQNj的C1级容器、及其邻居中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，返回查询失败；
    步骤4)、对于任意满足1≤i≤I-1，检查是否满足Ti≤Ts＜Ti+1：若满足Ti≤Ts＜Ti+1，则转至下一步骤，若不满足Ti≤Ts＜Ti+1，则跳转至步骤7)；
    步骤5)、当Ti≤Ts＜Ti+1时，将查询请求转发给含有LQNj的Ci级容器的查询节点，记为Cik，则在该Cik及其邻居列表{Cim}中进行初步查询：若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则返回查询失败；优选地，在该Cik及其邻居列表{Cim}中的布隆滤波器BF中进行查询；
    步骤6)、在该Cik及其邻居列表{Cim}中查询；若查询到标识符所对应的网络地址，则直接返回查询结果，若没有查询到标识符所对应的网络地址，则返回查询失败；优选地，在该Cik及其邻居列表{Cim}中的分布式哈希表DHT中进行查询；
    步骤7)、在含有LQNj的CI级容器中进行初步查询；若查询到标识符所对应的网络地址，则转至下一步骤；若没有查询到标识符所对应的网络地址，则跳转至步骤9)；优选地，步骤7)中，在含有LQNj的CI级容器中的布隆滤波器BF中进行初步查询；
    步骤8)、在含有LQNj的CI级容器中进行查询；若查询到标识符所对应的网络地址，则直接返回查询结果；若没有查询到标识符所对应的网络地址，则转至下一步骤；优选地，步骤8)中，在含有LQNj的CI级容器中的分布式哈希表DHT中进行查询。
PCT/CN2017/117698 2017-09-18 2017-12-21 一种基于时延构建弹性现场的查询增强系统及方法 WO2019052075A1 (zh)

Priority Applications (7)

Application Number Priority Date Filing Date Title
SG11202000879VA SG11202000879VA (en) 2017-09-18 2017-12-21 Query enhancement system and method for constructing elastic field based on time delay
KR1020207002421A KR102367540B1 (ko) 2017-09-18 2017-12-21 시간 지연에 기반한 탄성 필드 구축의 조회 강화 시스템 및 방법
US16/632,900 US11386103B2 (en) 2017-09-18 2017-12-21 Query enhancement system and method for constructing elastic field based on time delay
EP17925418.0A EP3686757A4 (en) 2017-09-18 2017-12-21 INTERROGATION IMPROVEMENT SYSTEM AND METHOD FOR BUILDING AN ELASTIC FIELD AS A FUNCTION OF PROPAGATION TIME
AU2017431351A AU2017431351B2 (en) 2017-09-18 2017-12-21 Query enhancement system and method for constructing elastic field based on time delay
JP2020515243A JP6992168B2 (ja) 2017-09-18 2017-12-21 クエリ拡張システム及びクエリ拡張方法
RU2020102290A RU2760243C2 (ru) 2017-09-18 2017-12-21 Система и способ улучшения запроса для создания распределяемой группы ресурсов на основании временной задержки

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710841537.4A CN109947764B (zh) 2017-09-18 2017-09-18 一种基于时延构建弹性现场的查询增强系统及方法
CN201710841537.4 2017-09-18

Publications (1)

Publication Number Publication Date
WO2019052075A1 true WO2019052075A1 (zh) 2019-03-21

Family

ID=65722365

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/117698 WO2019052075A1 (zh) 2017-09-18 2017-12-21 一种基于时延构建弹性现场的查询增强系统及方法

Country Status (9)

Country Link
US (1) US11386103B2 (zh)
EP (1) EP3686757A4 (zh)
JP (1) JP6992168B2 (zh)
KR (1) KR102367540B1 (zh)
CN (1) CN109947764B (zh)
AU (1) AU2017431351B2 (zh)
RU (1) RU2760243C2 (zh)
SG (1) SG11202000879VA (zh)
WO (1) WO2019052075A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109729514B (zh) * 2017-10-30 2020-07-17 中国科学院声学研究所 一种移动网络实体的动态位置信息的快速查询方法
CN111651478A (zh) * 2020-06-10 2020-09-11 孙明松 一种运维信息查询系统及方法
CN115499285B (zh) * 2021-06-18 2023-11-24 中国科学院声学研究所 一种分布式分级时延提供的名字解析系统构建方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080195584A1 (en) * 2007-02-09 2008-08-14 Microsoft Corporation Communication Efficient Spatial Search in a Sensor Data Web Portal
CN103207897A (zh) * 2013-03-15 2013-07-17 北京京东世纪贸易有限公司 一种分布式存储查询系统及其运行方法和运行装置
CN106844666A (zh) * 2017-01-20 2017-06-13 北京理工大学 一种自适应的时间序列数据查询方法
CN107079044A (zh) * 2014-09-25 2017-08-18 交互数字专利控股公司 用于内容感知缓存的过程和用于多点协作传输的无线电资源管理

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7747757B2 (en) 2000-11-17 2010-06-29 Computer Associates Think, Inc. Distributed network query
EP1594278A1 (en) * 2004-05-04 2005-11-09 Hitachi, Ltd. Method and apparatus for disseminating, storing and collecting information in a communication network
US8331263B2 (en) * 2006-01-23 2012-12-11 Microsoft Corporation Discovery of network nodes and routable addresses
US9122720B2 (en) * 2011-06-14 2015-09-01 Microsoft Technology Licensing, Llc Enriching database query responses using data from external data sources
JP5800422B2 (ja) * 2011-11-07 2015-10-28 国立大学法人広島大学 連想メモリ
JP5740652B2 (ja) 2012-03-28 2015-06-24 株式会社日立製作所 計算機システム及びサブシステム管理方法
WO2014118938A1 (ja) 2013-01-31 2014-08-07 株式会社日立製作所 通信経路の管理方法
CN103401953B (zh) * 2013-07-18 2016-07-06 东南大学 一种基于双层结构的端到端的语音通信节点寻址方法
CN105721182B (zh) * 2014-12-03 2018-11-13 中国科学院声学研究所 一种树结构网络的管理结构分裂方法
US10015106B1 (en) * 2015-04-06 2018-07-03 EMC IP Holding Company LLC Multi-cluster distributed data processing platform
WO2017007990A1 (en) * 2015-07-08 2017-01-12 Convida Wireless, Llc M2m clustering management
CN105049550A (zh) * 2015-08-14 2015-11-11 电子科技大学 一种基于D1HT+Chord的名址分离映射系统
US10868742B2 (en) * 2017-03-29 2020-12-15 Juniper Networks, Inc. Multi-cluster dashboard for distributed virtualization infrastructure element monitoring and policy control
US10673714B1 (en) * 2017-03-29 2020-06-02 Juniper Networks, Inc. Network dashboard with multifaceted utilization visualizations

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080195584A1 (en) * 2007-02-09 2008-08-14 Microsoft Corporation Communication Efficient Spatial Search in a Sensor Data Web Portal
CN103207897A (zh) * 2013-03-15 2013-07-17 北京京东世纪贸易有限公司 一种分布式存储查询系统及其运行方法和运行装置
CN107079044A (zh) * 2014-09-25 2017-08-18 交互数字专利控股公司 用于内容感知缓存的过程和用于多点协作传输的无线电资源管理
CN106844666A (zh) * 2017-01-20 2017-06-13 北京理工大学 一种自适应的时间序列数据查询方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3686757A4

Also Published As

Publication number Publication date
JP6992168B2 (ja) 2022-01-13
RU2020102290A3 (zh) 2021-07-21
CN109947764B (zh) 2020-12-22
EP3686757A1 (en) 2020-07-29
AU2017431351B2 (en) 2021-03-11
EP3686757A4 (en) 2021-06-16
RU2760243C2 (ru) 2021-11-23
US20200167357A1 (en) 2020-05-28
RU2020102290A (ru) 2021-07-21
KR20200019994A (ko) 2020-02-25
SG11202000879VA (en) 2020-04-29
US11386103B2 (en) 2022-07-12
KR102367540B1 (ko) 2022-02-24
JP2020533922A (ja) 2020-11-19
AU2017431351A1 (en) 2020-02-06
CN109947764A (zh) 2019-06-28

Similar Documents

Publication Publication Date Title
US8166074B2 (en) Index data structure for a peer-to-peer network
CN106161610A (zh) 一种分布式存储的方法和系统
KR101640185B1 (ko) 그래프 데이터용 분산형 캐시
CN111177486B (zh) 一种分布式图计算过程中的消息传递方法和装置
WO2023087605A1 (zh) 服务编排方法、装置、系统及存储介质
CN103236989B (zh) 一种内容分发网络中的缓存控制方法、设备及系统
WO2019052075A1 (zh) 一种基于时延构建弹性现场的查询增强系统及方法
CN103617276A (zh) 一种分布式层次化的rdf数据的存储方法
US20220374407A1 (en) Multi-tenant partitioning in a time-series database
CN113641869B (zh) 一种人机物融合环境下的数字对象访问方法和系统
US20180205790A1 (en) Distributed data structure in a software defined networking environment
JP6913828B2 (ja) モバイルネットワークエンティティの動的位置情報の高速クエリー方法
WO2021017907A1 (zh) 一种优化的微服务间通信的方法及装置
CN113010373A (zh) 数据监控方法、装置、电子设备及存储介质
CN102572602B (zh) 在p2p直播流系统中基于dht的分布式索引实现方法
Zhou et al. Distributed query processing in an ad-hoc semantic web data sharing system
WO2019052076A1 (zh) 一种同层无交集全覆盖嵌套容器生成方法及可读存储介质
CN109981698B (zh) 基于元数据的数联网跨域数据访问标准化系统及方法
CN115865844B (zh) 基于sdn与ndn的虚实结合动态流量调度方法及装置
US20230344904A1 (en) Method, electronic device, and computer program product for looking up data
US11456889B2 (en) Information notification method, apparatus, and system
Yao et al. Minerva: Decentralized Collaborative Query Processing over InterPlanetary File System
Jiang et al. An improved resource query and location algorithm based on cloud computing
CN114997468A (zh) 基于多通道边缘计算和区块链的智能制造框架设计方法
CN110113398A (zh) 一种基于HBase的大规模无线传感网络数据存储系统

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 20207002421

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2017431351

Country of ref document: AU

Date of ref document: 20171221

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17925418

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020515243

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2017925418

Country of ref document: EP

Effective date: 20200420