CN108632357A - A kind of data center network region partitioning method, device and equipment - Google Patents
A kind of data center network region partitioning method, device and equipment Download PDFInfo
- Publication number
- CN108632357A CN108632357A CN201810321126.7A CN201810321126A CN108632357A CN 108632357 A CN108632357 A CN 108632357A CN 201810321126 A CN201810321126 A CN 201810321126A CN 108632357 A CN108632357 A CN 108632357A
- Authority
- CN
- China
- Prior art keywords
- network
- data center
- energy storage
- region
- center network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0659—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0677—Localisation of faults
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
A kind of data center network region partitioning method of present invention offer, device and equipment.The method includes：According to the structural parameters of data center network, the network energy storage characteristic matrix of the data center network is obtained；The network energy storage characteristic matrix is used to describe connection and energy storage relationship between the server of the data center network；Based on preset number of regions K, the spectral clustering that characteristic value quantity is K is done to the network energy storage characteristic matrix, obtains the region corresponding to each target device of the data center network；Region corresponding to each target device carries out region division, and the data center network is divided into K region.Region division is carried out through the invention, shields the minutia of region energy scheduling, and energy management scheduling rapidly and efficiently may be implemented.
Description
Technical field
The present embodiments relate to networks to divide field more particularly to a kind of data center network region partitioning method, dress
It sets and equipment.
Background technology
Currently, with the rapid development of energy internet, efficiently count using user as the service theory of core and quickly
Enormous impact is produced to management philosophy such as the productions, management, consumption of traditional energy industry according to interconnection platform.Compared to traditional electricity
Net, energy internet are emphasized using user as the production of core, the information of consumer unit and data interconnection, to promote new energy to disappear
It receives.Its basic goal is the power demand docking for the power generation needs and power consumer for making new energy enterprise by data interconnection, is led to
It crosses Electric control and fully matches supply and demand, to promote the utilization of new energy, improve the service efficiency of the energy.
The important information communications infrastructure of energy internet is the data center based on big data and cloud computing technology.Number
It is the product of Information and Communication Technology, power electronic technique, computer technology and Internet technology depth integration according to center, it can be with
It realizes extensive, high speed information data processing, transimission and storage, is the main support of energy internet intelligentization operation,
It is modern society's system operation " intelligence brain ".
Data center can be referred to as " cloud ", and cloud include intensive isomorphism or isomerism calculates, communicate and storage resource.
Either public cloud, private clound or mixed cloud, provide unit by resource of virtual machine, the calculating of specific corresponding different model,
Communication and storage entity.With the continuous development of data center, the quantity and performance of related resource are in volatile growth trend,
Isomerism is also continuously increased, this undoubtedly increases the processing of related service, transmission delay and multiple while performance is substantially improved
Miscellaneous degree, but its requirement (such as bandwidth, processing delay) to quality of service is growing on and on, and this gives the management and scheduling of data center
Bring great challenge.Isomerism based on computational entity and quantity intensive, it is necessary to carry out subregion layering to it, divide
Grade management, therefore data center's region division becomes essential key technology, is that data center carries out energy management, appoints
Business management, fault management and energy-saving main support.
Data center's region division is similar to traditional Grid and divides, and the division of traditional Grid is generally basede on ground
Domain interval etc..But with the continuous propulsion of urbanization process, the industrial park of super large geographic range, urban area are by continuous shape
At.The region partitioning method according to region interval traditional at this time will be no longer applicable in.
Invention content
In view of the problems of the existing technology, the embodiment of the present invention provide a kind of data center network region partitioning method,
Device and equipment are suitable for the development of urbanization process, and subregion, shielding are carried out according to the network architecture parameters of super large data center
Energy management and scheduling may be implemented more quickly and efficiently in the minutia of region energy scheduling.
In a first aspect, the embodiment of the present invention provides a kind of data center network region partitioning method, including：
According to the structural parameters of data center network, network-energy storage characteristic matrix of the data center network is obtained；Institute
State the connection between server of the network-energy storage characteristic matrix for describing the data center network and energy storage relationship；
Based on preset number of regions K, the spectral clustering that characteristic value quantity is K is carried out to the network-energy storage characteristic matrix,
The region corresponding to each target device of the data center network is obtained, K is the integer more than 1；
Region corresponding to each target device carries out region division, and the data center network is divided into K
Region.
Second aspect, the embodiment of the present invention provide a kind of data center network region division device, including：
Network-energy storage characteristic module obtains the data center network for the structural parameters according to data center network
Network-energy storage characteristic matrix；The network-energy storage characteristic matrix is used to describe between the server of the data center network
Connection and energy storage relationship；
Spectral clustering module carries out characteristic value for being based on preset number of regions K to the network-energy storage characteristic matrix
Quantity is the spectral clustering of K, obtains the region corresponding to each target device of the data center network, and K is whole more than 1
Number；And
Region division module carries out region division, by the data for the region corresponding to each target device
Central site network is divided into K region.
The third aspect, an embodiment of the present invention provides a kind of data center network region division equipment, which is characterized in that packet
It includes：
At least one processor；And
At least one processor being connect with the processor communication, wherein：
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
Order is able to carry out described in first aspect data center network region partitioning method of the embodiment of the present invention and its any alternative embodiment
Method.
Fourth aspect provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Matter stores computer instruction, and the computer instruction executes data center network region described in first aspect of the embodiment of the present invention and draws
Divide the method for method and its any alternative embodiment.
A kind of data center network region partitioning method provided in an embodiment of the present invention, passes through the structure of data center network
The revealed connection and energy storage relationship of parameter carries out network-energy storage characteristic Spectral radius cluster, network is taken into account in region division
Connection, energy, electric power and electrical efficiency problem are suitable for the development of urbanization process, realize that optimal network area is drawn
Point；Network area division is carried out through the embodiment of the present invention, shields the minutia of region energy scheduling, energy may be implemented
Management and scheduling are more quickly and efficiently.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of data center network region partitioning method flow diagram of the embodiment of the present invention；
Fig. 2 is data center network partition management schematic diagram of the embodiment of the present invention；
Fig. 3 is a kind of block schematic illustration of data center network region division equipment of the embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
The every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Fig. 1 is a kind of data center network region partitioning method flow diagram of the embodiment of the present invention, number as shown in Figure 1
According to central site network region partitioning method, including：
S100 obtains network-energy storage characteristic square of the data center network according to the structural parameters of data center network
Battle array；The network-energy storage characteristic matrix is used to describe connection and energy storage relationship between the server of the data center network
Specifically, the structural parameters include connection bandwidth between server, connection time delay, energy storage device capacity, electricity
Power transimission power and power transmission efficiency.
Specifically, data center network described in the embodiment of the present invention refers to forming data based on big data and cloud computing technology
The energy internet at center.The energy internet includes multiple servers, and each server is respectively connected with energy storage device, also
Including energy router, the energy router route for realizing network.
In step S100, network connection bandwidth in statistical data central site network between each two server, every two are needed
The mutual electric power of capacity, the energy storage device of network delay, the mating energy storage device of each server between a server
Transmit the mutual power transmission efficiency etc. of maximum power, energy storage device.Then it is built according to the network architecture parameters of acquirement
Eigenmatrix.
S200 is based on preset number of regions K, and the spectrum that characteristic value quantity is K is carried out to the network-energy storage characteristic matrix
Cluster, obtains the region corresponding to each target device of the data center network, and K is the integer more than 1；
Specifically, the preset number of regions K, expression, which is scheduled to the data center network, will be divided into K region；
The spectral clustering that characteristic value quantity is K is done to network-energy storage characteristic matrix, obtains a N-dimensional vector S1×N, S1×NMiddle element is
Integer between [1, K] corresponds to the region belonging to each target device of the data center network respectively.
Specifically, the target device can be energy router.
S300, the region corresponding to each target device carry out region division, the data center network are divided
For K region.
Specifically, after step S200 obtains the corresponding region of each target device, then the target device in K region is with regard to true
It is fixed, to which data center network is divided into K region according to the region belonging to each target device.
The embodiment of the present invention carries out net by the revealed connection and energy storage relationship of structural parameters of data center network
Network-energy storage characteristic Spectral radius cluster, network connection, energy, electric power and electrical efficiency problem are taken into account in region division,
Suitable for the development of urbanization process, realize that optimal network area divides；Network area is carried out through the embodiment of the present invention to draw
Point, the minutia of region energy scheduling is shielded, energy management and scheduling may be implemented more quickly and efficiently
In an alternative embodiment, step S100, the structural parameters according to data center network, described in acquisition
The network of data center network-energy storage characteristic matrix, specifically includes：
S100.1 obtains network connection according to the connection bandwidth and connection time delay between the server of data center network
Eigenmatrix；
Specifically, assuming the number N of the server of data center network, and IDC is numbered to it1,IDC2,…IDCN。
It is assumed that server ID CjWith server ID CiThere is network connection between (i ≠ j), its network connection bandwidth is tested respectively, with such
It pushes away, obtains the network bandwidth between any two server in data center network.
Specifically, assuming server ID CjWith server ID CiThere is network connection between (i ≠ j), tests its network company respectively
Time delay (μ s) is connect, and so on, obtain the network delay (ms) in data center between any two server.
S100.2, according to the power transmission between the energy storage device capacity of the server of data center network, energy storage device
Power and circuit transmission efficiency obtain energy storage connection features matrix；
Specifically, assuming server ID C1The capacity of the energy storage device of connection is p1(kW/h), respectively with server ID C1,
IDC2,…IDCNFor node, the capacity of the energy storage device respectively connected on each server is obtained；
Specifically, assuming server ID CjEnergy storage device and server ID CiThere is electric power between the energy storage device of (i ≠ j)
Connection, respectively obtains the maximum power of its power transmission, and so on, obtain any two server in data center network
Power transmission power between energy storage device.
It is assumed that server ID CjEnergy storage device and server ID CiHave between the energy storage device of (i ≠ j) it is electrically connected, point
The efficiency of transmission of its power transmission is not obtained, and so on, the energy storage for obtaining any two server in data center network is set
Power transmission efficiency between standby.
S100.3 is obtained according to the network connection eigenmatrix and the energy storage connection features matrix in the data
The network of heart network-energy storage characteristic matrix.
Specifically, the network connection eigenmatrix and the energy storage connection features matrix are overlapped, institute is acquired
State network-energy storage characteristic Matrix C of data center networkN×N：
CN×N=TBN×NPQEN×N,
Wherein, TBN×NFor network connection eigenmatrix, PQEN×NFor energy storage connection features matrix.
Based on above-described embodiment, step S100.1, the connection bandwidth between the server according to data center network
With connection time delay, network connection eigenmatrix is obtained, is specifically included：
For arbitrarily there is two servers of connection relation in the data center network, obtain described two servers it
Between connection bandwidth, obtain network connection bandwidth matrices BN×N：
Wherein, bIj, i=1 ..., N, j=1 ..., NConnection bandwidth between server i and server j；
For arbitrarily there is two servers of connection relation in the data center network, obtain described two servers it
Between connection time delay, obtain network connection time delay matrix TN×N：
Wherein, tIj, i=1 ..., N, j=1 ..., NConnection time delay between server i and server j；
According to the network connection bandwidth matrices BN×NWith the network connection time delay matrix TN×N, obtain network connection spy
Levy matrix TBN×N：
TBN×N=BN×N·/TN×N。
Based on above-described embodiment, step S100.2, according to the energy storage device capacity of the server of data center network, energy storage
Power transmission power between equipment and circuit transmission efficiency obtain energy storage connection features matrix, specifically include：
Obtain the energy storage device capacity of each server of the data center network, and by the energy storage device capacity pair
Angling obtains diagonal matrix PN×N=diag (p1,p2…pN), wherein pI, i=1 ..., NBy the server i energy storage devices connected
Capacity；
For arbitrarily there is the energy storage device of the two of connection relation servers, the energy storage device of described two servers is obtained
Between power transmission power, obtain power transmission power matrix QN×N：
Wherein, qIj, i=1 ..., N, j=1 ..., NElectric power between the energy storage device and the energy storage device for servicing j of server i passes
Defeated power；
For arbitrarily there is the energy storage device of the two of connection relation servers, the energy storage device of described two servers is obtained
Between power transmission efficiency, obtain power transmission efficiency matrix EN×N：
Wherein, eIj, i=1 ..., N, j=1 ..., NElectric power between the energy storage device and the energy storage device for servicing j of server i passes
Defeated efficiency；
According to the diagonal matrix PN×N, the power transmission power matrix QN×NWith the power transmission efficiency matrix
EN×N, obtain energy storage connection features matrix PQEN×N：
PQEN×N=PN×N·QN×N·EN×N。
Fig. 2 is data center network partition management schematic diagram of the embodiment of the present invention, referring to FIG. 2, above-described embodiment passes through
The structural parameters for obtaining data center network, i.e., between the connection bandwidth, any two server between any two server
Connection time delay, the energy storage device capacity of each server, the power transmission power between the energy storage device of any two server
Power transmission efficiency between the energy storage device of any two server, construction feature matrix, including network connection feature square
Battle array and network connection eigenmatrix, and network-energy storage spy is established by network connection eigenmatrix and network connection eigenmatrix
Matrix is levied, by carrying out spectral clustering to network-energy storage characteristic matrix, to carry out network area division；It needs to partition the network into
For several regions, it is assumed that it needs to be divided into K region, then the spectral clustering that characteristic value is K is carried out to network-energy storage characteristic matrix,
To which key equipment is divided into corresponding region, region division is completed.
Based on above-described embodiment, step S300, the region corresponding to each target device of basis carries out region division,
The data center network is divided into K region, further includes later：
The management entity in each region of the data center network energy in respective region is managed respectively and
Scheduling realizes the integral energy equilibrium of supply and demand by way of disperseing to cooperate；And/or
The management entity in each region of the data center network respectively carries out the matched business of institute in respective region
It selects and optimizes the resource in region；It is interregional through consultation or the mode of game realizes the scheduling and distribution of related service.
It, can be real according to the region after division after region division by the complete paired data central site network of above-described embodiment
The now energy management and service management in each region.Specifically, each region can select a computer (or corresponding meter
Calculate resource) management entity (or be administrator) as the region, operation and scheduling to resource entity in region carry out pipe
Reason.
When data center network needs to carry out energy management and scheduling, according to region division and each region interior joint
Generated energy and load approximation, energy management and scheduling can be first carried out inside region, the equilibrium of supply and demand is realized, works as region
When inside cannot achieve the equilibrium of supply and demand, the equilibrium of supply and demand is being realized by interregional energy scheduling.Because shielding region energy
The minutia of scheduling, region division can be managed to enable buret and be dispatched more quickly and efficiently.Specifically, when needing to data
When energy expenditure in central site network is managed and controls, each district management entity the energy in region is managed and
Scheduling, and by way of disperseing to cooperate, realize the integral energy equilibrium of supply and demand of data center network.
When carrying out traffic assignments and scheduling, data center network is needed according to business and calculating, is communicated and storage resource
Matching, complete intelligentized service management and scheduling.After region division, the homogeney of related resource is to phase in region
The concurrency operation and scheduling for closing program bring great convenience, and avoid the wasting of resources.By the task of a certain category feature point
Resource entity with matching characteristic in one region of dispensing, will be brought observability to the runnability of business, it is controllable and
Manageability is promoted, and is also brought convenience to troubleshooting, to promote the overall performance of data center.Specifically, when needs pair
When the business of data center is managed and controls, each district management entity selects the matched business of institute, and then
The resource optimized in distribution region completes correlation computations, communication and store tasks.It is interregional can through consultation or the side of game
Formula realizes the scheduling and distribution of related service.
Based on above-described embodiment, step S300, the region corresponding to each target device of basis carries out region division,
The data center network is divided into K region, further includes later：
When an error occurs, the management entity of fault zone carries out fault detect to compass of competency, and according to fault detect
Situation sends status information to adjacent area, to assist the fault location of adjacent area.
After region division by the complete paired data central site network of above-described embodiment, after carrying out region division, failure is fixed
Position complexity will greatly reduce, positioning accuracy can also be greatly improved, and based in region related resource entity it is same
Matter, reliability and Fault Isolation, the restorability of fault location will also greatly enhance, and avoid complicated fault location algorithm
With a large amount of consumption to computing resource.Specifically, when an error occurs, each district management entity carries out event to one's respective area resource
Barrier judgement, since region scale is much smaller than the scale of entire data center network, fault verification will become simpler and efficient.
According to fault detect situation, district management entity sends status information to adjacent area, to assist the fault location of adjacent area.
After realizing fault location, the isolation and reparation to defective device can be realized by one's respective area management entity, greatly improves event
Hinder treatment effeciency.
Further, when needing to realize the energy-saving target of data center network, the characteristics of different zones are according to itself
Adaptive energy-saving strategy is formulated, using respectively suitable energy conservation, to realize the maximization of energy-saving effect.Together
When, it is interregional, by having complementary advantages, to be realized by way of cooperation for the energy saving task that single region is difficult to complete
It is energy-saving.
When great change occurs for network state (topological change, resource distribution, physical make-up etc.), need triggering to data
The management region of central site network is repartitioned, and reassigns district management entity, realizes automation, processing management, with
Ensure the high efficiency of data center network operation.
The embodiment of the present invention also provides a kind of data center network region division device, including：
Network-energy storage characteristic module obtains the data center network for the structural parameters according to data center network
Network-energy storage characteristic matrix；The network-energy storage characteristic matrix is used to describe between the server of the data center network
Connection and energy storage relationship；
Spectral clustering module carries out characteristic value for being based on preset number of regions K to the network-energy storage characteristic matrix
Quantity is the spectral clustering of K, obtains the region corresponding to each target device of the data center network, and K is whole more than 1
Number；And
Region division module carries out region division, by the data for the region corresponding to each target device
Central site network is divided into K region.
The device of the embodiment of the present invention can be used for executing data center network region partitioning method embodiment shown in FIG. 1
Technical solution, implementing principle and technical effect are similar, and details are not described herein again.
Fig. 3 is the block schematic illustration of data center network region division equipment of the embodiment of the present invention.Referring to FIG. 3, described
Equipment, including：Processor (processor) 310, communication interface (Communications Interface) 320, memory
(memory) 330 and bus 340, wherein processor 310, communication interface 320, memory 330 are completed mutually by bus 340
Between communication.Processor 310 can call the logical order in memory 330, to execute following method, including：According to data
The structural parameters of central site network obtain network-energy storage characteristic matrix of the data center network；Network-the energy storage characteristic
Matrix is used to describe connection and energy storage relationship between the server of the data center network；Based on preset number of regions K,
The spectral clustering that characteristic value quantity is K is carried out to the network-energy storage characteristic matrix, obtains each mesh of the data center network
Region corresponding to marking device, K are the integer more than 1；Region corresponding to each target device carries out region division, will
The data center network is divided into K region.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer readable storage medium, the computer program include program instruction, when described program instructs quilt
When computer executes, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including：According to data center
The structural parameters of network obtain network-energy storage characteristic matrix of the data center network；The network-energy storage characteristic matrix
Connection between server for describing the data center network and energy storage relationship；Based on preset number of regions K, to institute
It states network-energy storage characteristic matrix and carries out the spectral clustering that characteristic value quantity is K, each target for obtaining the data center network is set
Standby corresponding region, K are the integer more than 1；Region corresponding to each target device carries out region division, will be described
Data center network is divided into K region.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer instructs, and the computer instruction makes the computer execute the side that above-mentioned each method embodiment is provided
Method, such as including：According to the structural parameters of data center network, network-energy storage characteristic square of the data center network is obtained
Battle array；The network-energy storage characteristic matrix is used to describe connection and energy storage relationship between the server of the data center network；
Based on preset number of regions K, characteristic value quantity is carried out for the spectral clustering of K, described in acquisition to the network-energy storage characteristic matrix
Region corresponding to each target device of data center network, K are the integer more than 1；Corresponding to each target device
Region carry out region division, the data center network is divided into K region.
One of ordinary skill in the art will appreciate that：Realize that above equipment embodiment or embodiment of the method are only schematic
, wherein can be that physically separate component may not be physically separated for the processor and the memory, i.e.,
A place can be located at, or may be distributed over multiple network units.It can select according to the actual needs therein
Some or all of module achieves the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creative labor
In the case of dynamic, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be expressed in the form of software products in other words, should
Computer software product can store in a computer-readable storage medium, such as USB flash disk, mobile hard disk, ROM/RAM, magnetic disc, CD
Deng, including some instructions use is so that a computer equipment (can be personal computer, server or the network equipment etc.)
Execute the method described in certain parts of each embodiment or embodiment.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of ordinary skill in the art that：It still may be used
With technical scheme described in the above embodiments is modified or equivalent replacement of some of the technical features；
And these modifications or replacements, various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of data center network region partitioning method, which is characterized in that including：
According to the structural parameters of data center network, network-energy storage characteristic matrix of the data center network is obtained；The net
Network-energy storage characteristic matrix is used to describe connection and energy storage relationship between the server of the data center network；
Based on preset number of regions K, the spectral clustering that characteristic value quantity is K is carried out to the network-energy storage characteristic matrix, is obtained
Region corresponding to each target device of the data center network, K are the integer more than 1；
Region corresponding to each target device carries out region division, and the data center network is divided into K region.
2. according to the method described in claim 1, it is characterized in that, the structural parameters according to data center network, obtain
The network of the data center network-energy storage characteristic matrix, specifically includes：
According to the connection bandwidth and connection time delay between the server of data center network, network connection eigenmatrix is obtained；
According to the power transmission power and circuit biography between the energy storage device capacity of the server of data center network, energy storage device
Defeated efficiency obtains energy storage connection features matrix；
According to the network connection eigenmatrix and the energy storage connection features matrix, the net of the data center network is obtained
Network-energy storage characteristic matrix.
3. according to the method described in claim 2, it is characterized in that, company between the server according to data center network
Tape splicing is wide and connection time delay, acquisition network connection eigenmatrix specifically include：
For arbitrarily there are two servers of connection relation in the data center network, obtain between described two servers
Bandwidth is connected, network connection bandwidth matrices B is obtainedN×N：
Wherein, bIj, i=1 ..., N, j=1 ..., NConnection bandwidth between server i and server j；
For arbitrarily there are two servers of connection relation in the data center network, obtain between described two servers
Time delay is connected, network connection time delay matrix T is obtainedN×N：
Wherein, tIj, i=1 ..., N, j=1 ..., NConnection time delay between server i and server j；
According to the network connection bandwidth matrices BN×NWith the network connection time delay matrix TN×N, obtain network connection eigenmatrix
TBN×N：
TBN×N=BN×N·/TN×N。
4. according to the method described in claim 2, it is characterized in that, being held according to the energy storage device of the server of data center network
Power transmission power between amount, energy storage device and circuit transmission efficiency obtain energy storage connection features matrix, specifically include：
Obtain the energy storage device capacity of each server of the data center network, and by the energy storage device capacity diagonalization
Obtain diagonal matrix PN×N=diag (p1,p2…pN), wherein pI, i=1 ..., NBy the appearance of the server i energy storage devices connected
Amount；
For arbitrarily there is an energy storage device of the two of connection relation servers, between the energy storage device for obtaining described two servers
Power transmission power, obtain power transmission power matrix QN×N：
Wherein, qIj, i=1 ..., N, j=1 ..., NFor the power transmission work(between the energy storage device and the energy storage device for servicing j of server i
Rate；
For arbitrarily there is an energy storage device of the two of connection relation servers, between the energy storage device for obtaining described two servers
Power transmission efficiency, obtain power transmission efficiency matrix EN×N：
Wherein, eIj, i=1 ..., N, j=1 ..., NFor the power transmission effect between the energy storage device and the energy storage device for servicing j of server i
Rate；
According to the diagonal matrix PN×N, the power transmission power matrix QN×NWith the power transmission efficiency matrix EN×N, obtain
To energy storage connection features matrix PQEN×N：
PQEN×N=PN×N·QN×N·EN×N。
5. according to the method described in claim 2, it is characterized in that, described according to the network connection eigenmatrix and the storage
Energy connection features matrix, obtains network-energy storage characteristic matrix of the data center network, specifically includes：
The network connection eigenmatrix and the energy storage connection features matrix are overlapped, data center's net is acquired
The network of network-energy storage characteristic Matrix CN×N：
CN×N=TBN×NPQEN×N。
6. according to the method described in claim 1, it is characterized in that, the region corresponding to each target device of the basis carries out
The data center network is divided into K region, further includes later by region division：
The management entity in each region of the data center network is managed and dispatches to the energy in respective region respectively,
By way of disperseing to cooperate, the integral energy equilibrium of supply and demand is realized；And/or
The management entity in each region of the data center network respectively selects the matched business of institute in respective region
And optimize the resource in region；It is interregional through consultation or the mode of game realizes the scheduling and distribution of related service.
7. method according to claim 1 or 6, which is characterized in that the region corresponding to each target device of basis
Region division is carried out, the data center network is divided into K region, further includes later：
When an error occurs, the management entity of fault zone carries out fault detect to compass of competency, and according to fault detect situation
Status information is sent to adjacent area, to assist the fault location of adjacent area.
8. a kind of data center network region division device, which is characterized in that including：
Network-energy storage characteristic module obtains the net of the data center network for the structural parameters according to data center network
Network-energy storage characteristic matrix；The network-energy storage characteristic matrix is used to describe the company between the server of the data center network
It connects and energy storage relationship；
Spectral clustering module carries out characteristic value quantity for being based on preset number of regions K to the network-energy storage characteristic matrix
For the spectral clustering of K, the region corresponding to each target device of the data center network is obtained, K is the integer more than 1；With
And
Region division module carries out region division, by the data center for the region corresponding to each target device
Network is divided into K region.
9. a kind of data center network region division equipment, which is characterized in that including：
At least one processor；And
At least one processor being connect with the processor communication, wherein：
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough methods executed as described in claim 1 to 7 is any.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the method as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810321126.7A CN108632357B (en) | 2018-04-11 | 2018-04-11 | Data center network area division method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810321126.7A CN108632357B (en) | 2018-04-11 | 2018-04-11 | Data center network area division method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108632357A true CN108632357A (en) | 2018-10-09 |
| CN108632357B CN108632357B (en) | 2021-02-02 |
Family
ID=63704926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810321126.7A Active CN108632357B (en) | 2018-04-11 | 2018-04-11 | Data center network area division method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108632357B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111628893A (en) * | 2020-05-27 | 2020-09-04 | 星辰天合（北京）数据科技有限公司 | Fault processing method and device of distributed storage system and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034808A (en) * | 2007-03-23 | 2007-09-12 | 清华大学 | Distributed computing method of the features of the power system |
| CN103632203A (en) * | 2013-09-23 | 2014-03-12 | 国家电网公司 | Distribution network power supply area division method based on comprehensive evaluation |
| CN105356450A (en) * | 2015-10-28 | 2016-02-24 | 国家电网公司西北分部 | Power grid subarea division method based on dynamic electricity prices |
| CN105790279A (en) * | 2016-04-28 | 2016-07-20 | 西华大学 | Reactive voltage partitioning method based on spectral clustering |
| CN106203867A (en) * | 2016-07-19 | 2016-12-07 | 国家电网公司 | Grid division methods based on power distribution network assessment indicator system and cluster analysis |
| CN106329520A (en) * | 2016-09-21 | 2017-01-11 | 河海大学 | PSASP (Power System Analysis Software Package)-based UPFC (Unified Power Flow Controller) modeling method |
| US9749026B2 (en) * | 2013-04-12 | 2017-08-29 | Avago Technologies General Ip (Singapore) Pte. Ltd. | Spatial null creation using massive MIMO (M-MIMO) |
| CN107492887A (en) * | 2017-09-04 | 2017-12-19 | 清华大学 | A kind of region partitioning method and system of wide area energy internet |
-
2018
- 2018-04-11 CN CN201810321126.7A patent/CN108632357B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034808A (en) * | 2007-03-23 | 2007-09-12 | 清华大学 | Distributed computing method of the features of the power system |
| US9749026B2 (en) * | 2013-04-12 | 2017-08-29 | Avago Technologies General Ip (Singapore) Pte. Ltd. | Spatial null creation using massive MIMO (M-MIMO) |
| CN103632203A (en) * | 2013-09-23 | 2014-03-12 | 国家电网公司 | Distribution network power supply area division method based on comprehensive evaluation |
| CN105356450A (en) * | 2015-10-28 | 2016-02-24 | 国家电网公司西北分部 | Power grid subarea division method based on dynamic electricity prices |
| CN105790279A (en) * | 2016-04-28 | 2016-07-20 | 西华大学 | Reactive voltage partitioning method based on spectral clustering |
| CN106203867A (en) * | 2016-07-19 | 2016-12-07 | 国家电网公司 | Grid division methods based on power distribution network assessment indicator system and cluster analysis |
| CN106329520A (en) * | 2016-09-21 | 2017-01-11 | 河海大学 | PSASP (Power System Analysis Software Package)-based UPFC (Unified Power Flow Controller) modeling method |
| CN107492887A (en) * | 2017-09-04 | 2017-12-19 | 清华大学 | A kind of region partitioning method and system of wide area energy internet |
Non-Patent Citations (2)
| Title |
|---|
| 任光，曹军威，胡紫巍: "开放架构下能源胡亮网新能源接入功率控制方法研究", 《南方电网技术》 * |
| 盛四清: "基于遗传算法的地区电网停电恢复", 《电力系统自动化》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111628893A (en) * | 2020-05-27 | 2020-09-04 | 星辰天合（北京）数据科技有限公司 | Fault processing method and device of distributed storage system and electronic equipment |
| CN111628893B (en) * | 2020-05-27 | 2022-07-12 | 北京星辰天合科技股份有限公司 | Fault processing method and device of distributed storage system and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108632357B (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pires et al. | A virtual machine placement taxonomy | |
| CN107579518B (en) | Power system environment economic load dispatching method and apparatus based on MHBA | |
| Huang et al. | Energy-aware virtual machine placement in data centers | |
| CN108111931A (en) | The virtual resource section management method and device of a kind of power optical fiber access net | |
| CN108228724A (en) | Power grid GIS topology analyzing method and storage medium based on chart database | |
| Chen et al. | Multi-controller placement towards SDN based on Louvain heuristic algorithm | |
| Luo et al. | Reliable virtual machine placement based on multi-objective optimization with traffic-aware algorithm in industrial cloud | |
| CN104794541B (en) | A kind of power distribution network running optimizatin method based on simulated annealing and cone optimization | |
| CN109995580A (en) | VN mapping method based on GA_PSO hybrid algorithm in 5G network slice | |
| CN111221624A (en) | Container management method for regulation cloud platform based on Docker container technology | |
| Lin et al. | Research on resource self-organizing model for cloud computing | |
| Sarikaya et al. | Placement of 5G RAN slices in multi-tier O-RAN 5G networks with flexible functional splits | |
| CN106528265A (en) | Virtual machine management method and system based on distributed SAN (Storage Area Network) storage architecture | |
| Pavone et al. | Distributed policies for equitable partitioning: Theory and applications | |
| CN106877316B (en) | It is a kind of meter and controllable electric power economic load dispatching active distribution network net capability model construction method | |
| Zhu et al. | Double-agent reinforced vNFC deployment in EONs for cloud-edge computing | |
| Alharbe et al. | An improved ant colony algorithm for solving a virtual machine placement problem in a cloud computing environment | |
| Wu et al. | Resource allocation optimization in the NFV-enabled MEC network based on game theory | |
| CN108632357A (en) | A kind of data center network region partitioning method, device and equipment | |
| Zhou et al. | Big data and knowledge graph based fault diagnosis for electric power systems | |
| Wen et al. | Towards reliable virtual data center embedding in software defined networking | |
| CN109688068A (en) | Network load balancing method and device based on big data analysis | |
| Xia et al. | Distributed resource management and admission control of stream processing systems with max utility | |
| Alzahrani et al. | Energy-aware virtual network embedding approach for distributed cloud | |
| Xuan et al. | Energy efficiency opposition-based learning and brain storm optimization for vnf-sc deployment in iot |
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 |