CN105049475B - The data efficient storage optimization method and system of extensive community - Google Patents
The data efficient storage optimization method and system of extensive community Download PDFInfo
- Publication number
- CN105049475B CN105049475B CN201510273778.4A CN201510273778A CN105049475B CN 105049475 B CN105049475 B CN 105049475B CN 201510273778 A CN201510273778 A CN 201510273778A CN 105049475 B CN105049475 B CN 105049475B
- Authority
- CN
- China
- Prior art keywords
- data
- server
- algorithm
- storage
- central server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Abstract
The present invention provides the data efficient storage optimization method of extensive community, this method is implemented in the storage organization of multistage server, including, polymorphic type project level server reports the currently stored amount and frequency of use of local categorical data;Determine that algorithm is stored according to current desired central server quantity and the combined information of polymorphic type project level server to data are locally stored to obtain the combined information of current desired central server quantity and multiple project level servers after current algorithm.To which in the big data storing process for solving extensive community, the wasting of resources is more, system is equipped with uneven problem.Therefore, the data efficient storage optimization method and system of extensive community provided by the present invention, pass through the combination and optimization of the amount of storage to project level server, improve the utilization rate of central server, effectively reduce the usage quantity of central server, this improves the safety of system and stability.
Description
Technical field
The present invention relates to the technical field of wireless telecommunications, the data efficient storage optimization method of especially extensive community and
System.
Background technology
With the gradually development of intelligent Community, community service data volume is significantly promoted, to realize the peace of community data
Full property and reliability, it usually needs comprehensive, reliable multi-level backup structure is carried out to community data and is backed up.As used:Society
Area's grade server, project level server and central server backup architecture, but during the use of data backup, first, respectively
Community server it is not consistent with this and actual storage amount.Secondly, in storing process, easily there is larger central server
It is idle, on the one hand, to easily cause the decline of central server utilization rate, maintenance cost rises.On the other hand, cause security of system and
Storage efficiency reduces, and so that the flexibility of system and dilatancy is declined, to influence the normal operation of system.
Invention content
The defects of for the above-mentioned prior art, the present invention solves in the big data storing process of extensive community, money
Source waste is more, system is equipped with uneven problem.
In order to achieve the above object, the present invention provides the following technical solutions:
The data efficient storage optimization method of extensive community in the present invention, this method are implemented on depositing for multistage server
In storage structure, including,
Step S101:Polymorphic type project level server reports the currently stored amount and frequency of use of local categorical data;
Step S102:According to the pre- storage of separate unit central server, the currently stored amount of the local categorical data and institute
Frequency of use is stated, by algorithm one and algorithm two, obtains first total communication cost and second total communication cost respectively, according to
Algorithm corresponding to the small value of the communication cost is current algorithm;The algorithm one is service under the conditions of given number of servers
The optimization algorithm of the server storage of operation optimization, the algorithm two are that the optimization of the server storage of Service Operation optimization is calculated
Method;
Step S103:According to the current algorithm and the pre- storage of separate unit central server to multiple currently stored amounts
It is combined, obtains current desired central server quantity;Multiple projects are corresponded to according to the combined information of the currently stored amount
Grade server info, obtains the combined information of multiple project level servers;
When current algorithm is algorithm two, the specific steps of the step S103 include:
Polymorphic type project level server described in poll deposits any two or the current of multiple polymorphic type project level servers
Reserves are combined, and capability value is less than and is combined closest to multiple item servers of separate unit central server after obtaining combination;
The quantity combined according to the multiple item server determines current desired central server quantity;Or;
According to genuinely convinced in default Current central number of servers, the currently stored amount of polymorphic type project level server and separate unit
The pre- storage of business device establishes tree data structure, is scanned for the structure and beta pruning, obtains capability value after combination and is less than and most
Multiple item servers close to separate unit central server combine;The quantity combined according to the multiple item server determines the
Two current desired central server quantity;
Step S104:It is right according to current desired central server quantity and the combined information of polymorphic type project level server
Data are locally stored to be stored.
In a preferred embodiment, further include before the step S101:
Step S100, the polymorphic type project level server receive storage data from multiple community servers.
In a preferred embodiment, the step S101 includes,
It is described local categorical data type include:Property data, finance data, medical data, home control data and
Agreement and director data.
In a preferred embodiment, pre- storage, the local number of types according to separate unit central server
According to currently stored amount and the frequency of use the first total communication cost and the are obtained by algorithm one and algorithm two respectively
The step of two total communication costs includes:
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm one respectively, and the is obtained according to the diversiform data communication cost
One total communication cost;
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm two respectively, and the is obtained according to the diversiform data communication cost
Two total communication costs.
Meanwhile the data efficient storage optimization system of extensive community, which is characterized in that including polymorphic type project level clothes
Business device, central server and storage optimization processor;
The polymorphic type project level server reports the currently stored amount and frequency of use of local categorical data;
The polymorphic type project level server is worked as according to the pre- storage of separate unit central server, the local categorical data
Preceding amount of storage and the frequency of use obtain first total communication cost and second total by algorithm one and algorithm two respectively
Communication cost, the algorithm corresponding to small value according to the communication cost are current algorithm;The algorithm one is given server count
Under the conditions of amount, the optimization algorithm of the server storage of Service Operation optimization, the algorithm two is the server of Service Operation optimization
The optimization algorithm of storage;
Multiple currently stored amounts are combined according to the current algorithm and the pre- storage of separate unit central server,
Obtain current desired central server quantity;Multiple project level server letters are corresponded to according to the combined information of the currently stored amount
Breath, obtains the combined information of multiple project level servers;
When current algorithm is algorithm two, the polymorphic type project level server is additionally configured to:
Polymorphic type project level server described in poll deposits any two or the current of multiple polymorphic type project level servers
Reserves are combined, and capability value is less than and is combined closest to multiple item servers of separate unit central server after obtaining combination;
The quantity combined according to the multiple item server determines current desired central server quantity;Or;
According to genuinely convinced in default Current central number of servers, the currently stored amount of polymorphic type project level server and separate unit
The pre- storage of business device establishes tree data structure, is scanned for the structure and beta pruning, obtains capability value after combination and is less than and most
Multiple item servers close to separate unit central server combine;The quantity combined according to the multiple item server determines the
Two current desired central server quantity;
According to current desired central server quantity and the combined information of polymorphic type project level server, to number is locally stored
According to being stored.
In a preferred embodiment, the polymorphic type project level server is additionally configured to from multiple community servers
Receive storage data.
In a preferred embodiment, the type of the local categorical data includes:Property data, finance data,
Medical data, home control data and agreement and director data.
In a preferred embodiment, the polymorphic type project level server is additionally configured to:
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm one respectively, and the is obtained according to the diversiform data communication cost
One total communication cost;
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm two respectively, and the is obtained according to the diversiform data communication cost
Two total communication costs.
Beneficial effects of the present invention are:The data efficient storage optimization method of extensive community provided by the present invention and it is
System, by the combination and optimization of the amount of storage to project level server, improves the utilization rate of central server, effectively reduces
The usage quantity of central server, this improves the safety of system and stability.
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 only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is in one embodiment of the present invention, and the system of the data efficient storage optimization method of extensive community forms
Frame diagram;
Fig. 2 is in one embodiment of the present invention, and the flow of the data efficient storage optimization method of extensive community is illustrated
Figure;
Fig. 3 is in another embodiment of the present invention, and the flow of the data efficient storage optimization method of extensive community is shown
It is intended to.
Specific implementation mode
Below in conjunction with the attached drawing of the present invention, technical scheme of the present invention is clearly and completely described, it is clear that institute
The embodiment of description is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention,
The every other embodiment that those of ordinary skill in the art are obtained without creative efforts, belongs to this hair
The range of bright protection.
As shown in Figure 1, 2, in one embodiment of the present invention, the data efficient storage of the extensive community in the present invention
Optimization method is implemented in this method and is implemented in the storage organization of multistage server, which is A, B, C as shown in Figure 1
Three tier server, wherein:
(1) A grades of servers:Central server.
All data of B grades of servers are backed up, each B grades of server can be found on A grades of servers
Unique backup place;In addition, the storage data of A grades of servers, will be used for big data analysis, commercial operation is carried out.
(2) B grades of servers:Project level server.
Data for storing each smart city, intelligence community.
The a certain data of some intelligence community are only stored on each B grades of server.
The storage data class of B grades of servers includes:
1) property data;2) finance data;3) medical data;4) home control data;5) agreement and instruction
(3) C grades of servers:Community-level server.
The data class of B grades of server storages is identical as the data class of C grades of server storages.
B grades of servers are backed up with C grades of server syncs, have one-to-one relationship.
In one embodiment of the invention, the data efficient storage optimization method of extensive community, including:
Step S101:Report polymorphic type project level server info.
In this step, polymorphic type project level server reports the currently stored amount and frequency of use of local categorical data.
Step S102:Determine current algorithm.
In this step, according to the pre- storage of separate unit central server, the currently stored amount of the local categorical data and
The frequency of use obtains first total communication cost and second total communication cost, root respectively by algorithm one and algorithm two
The algorithm corresponding to small value according to the communication cost is current algorithm.
Step S103:Obtain the storage information of central server.
Multiple currently stored amounts are combined according to the current algorithm and the pre- storage of separate unit central server,
Obtain current desired central server quantity;Multiple project level server letters are corresponded to according to the combined information of the currently stored amount
Breath, obtains the combined information of multiple project level servers;
Step S104:Carry out data storage.
According to current desired central server quantity and the combined information of polymorphic type project level server, to number is locally stored
According to being stored.
It is above-mentioned local categorical data type include:Property data, finance data, medical data, home control data and
Agreement and director data.
As shown in figure 3, in a kind of preferred embodiment of the present invention, further include before the step S101:Step
S100, the polymorphic type project level server receive storage data from multiple community servers.
In a kind of preferred embodiment of the present invention, above-mentioned pre- storage according to separate unit central server, the local
The currently stored amount and the frequency of use of categorical data obtained for first total communication generation respectively by algorithm one and algorithm two
The step of valence and second total communication cost includes:
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm one respectively, and the is obtained according to the diversiform data communication cost
One total communication cost;
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm two respectively, and the is obtained according to the diversiform data communication cost
Two total communication costs.
It is above-mentioned according to the current algorithm when current algorithm is algorithm two in a kind of preferred embodiment of the present invention
And the pre- storage of separate unit central server is combined multiple currently stored amounts, obtains current desired central server number
Amount;Multiple project level server infos are corresponded to according to the combined information of the currently stored amount, obtain multiple project level servers
Combined information the step of include:
Polymorphic type project level server described in poll deposits any two or the current of multiple polymorphic type project level servers
Reserves are combined, and capability value is less than and is combined closest to multiple item servers of separate unit central server after obtaining combination;
The quantity combined according to the multiple item server determines current desired central server quantity;Or;
According to genuinely convinced in default Current central number of servers, the currently stored amount of polymorphic type project level server and separate unit
The pre- storage of business device establishes tree data structure, is scanned for the structure and beta pruning, obtains capability value after combination and is less than and most
Multiple item servers close to separate unit central server combine;The quantity combined according to the multiple item server determines the
Two current desired central server quantity.
Above-mentioned algorithm can specifically be given by following calculating process and be realized:
First, the mathematical model of the server storage of Service Operation optimization is established
Assuming that the memory capacity of B grades of servers of N platforms is respectively:W1, w2, w3 ..., wN;
The service type of B grades of servers of N platforms is respectively:S1, s2, s3 ..., sN (value of service type be 1,2,3,4,
5, wherein:1 indicates that property data, 2 indicate that finance data, 3 indicate that medical data, 4 indicate home control data, 5 presentation protocols
With instruction);
The operating frequency of each service type is P1, P2, P3, P4, P5;
The memory capacity of each A grades of servers is W;
The communication connection cost for connecting arbitrary two A grades of servers is C;
B grades of server B i (1≤i≤n) will be assigned on BXi (1≤BXi≤m) A grades of servers of K platforms;
Enable function
It is required that:Provide a server storage scheme, it is ensured that the communication cost of the Various types of data service access of A grades of servers
And minimum.
It is BX={ BX1, BX2 ..., BXn } to enable the solution vector of B grades of servers of n platforms, and (1≤BXi≤m) will when initialization
BXi (1≤i≤n) is all set to 0.
It enables function Fi (1≤i≤5) indicate, stores the A grade number of servers of i-th (1≤i≤5) class data.
Following mathematical model can be then provided,
Tree virtual presence in algorithm operational process does not need to explicitly build a tree.
Input:The service type of the memory capacity array B grades of servers of N platforms of B grades of servers of N platforms is respectively:S=s1,
S2 ..., sN }, si ∈ { 1,2,3,4,5 };The memory capacity W of each A grades of servers gives number of servers m;Each service
The operating frequency P={ p1, p2, p3, p4, p5 } of type
Output:The A grade server locations that total B grades of servers of communication cost FinalCommuCost, N platform are stored:BX
={ BX1, BX2 ..., BXn }, (1≤BXi≤m).
Step 1:(initialization)
FinalCommuCost=+ ∞;
Initialize the number of plies j=1 of tree extreme saturation;
Initialize solution vector:FORi=1 TO N DO
BXi=0;
END FOR
Step 2:(search is completed)
IF j==0 THEN
Go to step 6;
END IF
Step 3:(end condition of tree deep search)
IF j==n THEN
Whether n-th of component BXn of judgement solution BX meets constraint (1), (2), (3), (4);
IF BXn meet condition, THEN
Call function calculates present communications connection total cost CommuCost (BX);
IF CommuCost (BX) < FinalCommuCost THEN
FinalCommuCost=CommuCost (BX);
Preserve solution BX={ BX1, BX2 ..., BXn };
END IF
END IF
J=j-1;BXj=BXj+1;
Go to step 2;
END IF
Step 4:(end condition that tree is searched for next layer)
IF j < n THEN
Whether n-th of component BXn of judgement solution BX meets constraint (1), (2), (3), (4);
IFBXn meets condition, then j=j+1;Go to step 3;
END IF
END IF
Step 5:(tree beta pruning, and upper layer is recalled)
IF j < n THEN
Whether n-th of component BXn of judgement solution BX meets constraint (1), (2), (3), (4);
IF BXn are unsatisfactory for condition, then
IF BXj < m THEN BXj=BXj+1;(continuing search for working as the other branches of layer)
ELSE
J=j-1, BXj=BXj+1;(the next branch for tracing back to last layer)
END IF
Go to step 3;
END IF
END IF
Step 6:(output of solution)
Total communication cost FinalCommuCost is sequentially output BX={ BX1, BX2 ..., BXn }.
Int Function Fi(inti)
// calculate the A grade number of servers for storing i-th (1≤i≤5) class data.
Definition set:SetFi=φ;
FOR j=1 TO N DO
If the service data type of the storage of sj==iTHEN//B grades of server B Xj of IF is i
SetFi=SetFi ∪ { BXj };
END IF
END FOR
Element number Sum in statistics set SetFi;
Return Sum;
END Function
Int Function CommuCost(BX)
The communication connection total cost of the service type for the A grade servers that // statistics currently solves
Int CommuTotal=0;
5 DO of FOR i=1 TO
CommuTotal=CommuTotal+ (Fi (i) -1) × pi;
END FOR
Return CommuTotal;
END Function
Algorithm two:The optimization algorithm of the server storage of Service Operation optimization
Input:The service type of the memory capacity array B grades of servers of N platforms of B grades of servers of N platforms is respectively:S=s1,
S2 ..., sN }, s1 ∈ { 1,2,3,4,5 };The memory capacity W of each A grades of servers, the operating frequency P=of each service type
{ p1, p2, p3, p4, p5 }
Output:A grades of number of servers, the A grades that total B grades of servers of communication cost FinalCommuCost, N platform are stored
Server location:BX={ BX1, BX2 ..., BXn }, (1≤BXi≤m).
Step 1:Primarily determine the A grade number of servers MIN for meeting B grades of server storage capacity;
Calculate all data storage capacity values of B grades of servers:
IF Total MOD W==0 THEN MIN=Total/W;
ELSE MIN=Total/W+1;
END IF
Step 2:Minimum A grade number of servers m is searched for successively;
P=MIN;(assigning initial value to temporary variable P)
WHILE(P≥MIN)DO
Enable m=P;Call algorithm one;
IF BX={ 0,0 ..., 0 } THEN (algorithm one does not search suitable solution)
P=P+1;
ELSE
BX values are recorded successively;Go to step 3;
END IF
END WHILE
Step 3:The quantity m of export server;It is sequentially output total communication cost FinalCommuCost, is sequentially output BX
={ BX1, BX2 ..., BXn }.
Embodiment:
Provide the memory capacity table (as shown in table 1) of one 13 B grades of servers.
Table 2:The memory capacity table of one 13 B grades of servers
The access frequency of 3. all kinds of services of table
Service type | Property data | Finance data | Medical data | Home control data | Agreement and instruction |
Access frequency | 3000 | 10000 | 3000 | 20000 | 3000 |
Assuming that the communication connection cost between different A grades of servers is C;
Assuming that the total storage capacity of every A grades of servers is 25T;
If using non-optimal way, B grades of sequence servers are stored in A grades of servers, then, the storage side of B grades of servers
Formula is:
A1 servers are stored in:B1(10T)+B2(10T)+B3(5T);
A2 servers are stored in:B4(10T)+B5(9T)+B6(4T);
A3 servers are stored in:B7(3T)+B8(9T)+B9(8T);
A4 servers are stored in:B10(8T)+B11(8T)+B12(4T);
A5 servers are stored in:B13(9T).
5 A grades of servers are needed altogether.
1) the A grade servers that property data are related to are:A1, A2, A5, property data service cost are:
3000 × (3-1) × C=6000C;
2) the A grade servers that finance data is related to are:A1, A2, A4, finance data service cost are:
10000 × (3-1) × C=20000C
3) the A grade servers that medical data is related to are:A2, A4, medical data service cost are:
3000 × (2-1) × C=3000C
4) the A grade servers that home control data are related to are:A3, A4, home control data service cost are:
20000 × (2-1) × C=20000C
5) the A grade servers that agreement is related to director data are:A3, agreement are with director data service cost:
3000 × (1-1) × C=0
Therefore, total communication cost is:6000C+20000C+3000C+20000C=49000C
And use algorithm two, then only need 4 A grades of servers, used storage mode to be:
A1 servers are stored in:B1(10T)+B2(10T)+B3(5T);
A2 servers are stored in:B4(10T)+B7(3T)+B13(9T);
A3 servers are stored in:B5(9T)+B6(4T)+B11(8T)+B12(4T);
A4 servers are stored in:B8(9T)+B9(8T)+B10(9T);
1) the A grade servers that property data are related to are:A1, A2, property data service cost are:
3000 × (2-1) × C=4000C;
2) the A grade servers that finance data is related to are:A1, A3, finance data service cost are:
10000 × (2-1) × C=10000C
3) the A grade servers that medical data is related to are:A3, medical data service cost are:
3000 × (1-1) × C=0
4) the A grade servers that home control data are related to are:A4, home control data service cost are:
20000 × (1-1) × C=0
5) the A grade servers that agreement is related to director data are:A2, agreement are with director data service cost:
3000 × (1-1) × C=0
Therefore, total communication cost is:4000C+10000C=14000C
It therefore, can be with the memory space of effectively save server using algorithm two;The comprehensive of A grades of servers can also be improved
Close access, processing capacity.
Meanwhile the present invention also provides the data efficient storage optimization systems of extensive community, including, polymorphic type project level
Server, central server and storage optimization processor;
Meanwhile the present invention provides the data efficient storage optimization systems of extensive community, wherein including polymorphic type item
Mesh grade server, central server and storage optimization processor;
The polymorphic type project level server reports the currently stored amount and frequency of use of local categorical data;
The polymorphic type project level server is worked as according to the pre- storage of separate unit central server, the local categorical data
Preceding amount of storage and the frequency of use obtain first total communication cost and second total by algorithm one and algorithm two respectively
Communication cost, the algorithm corresponding to small value according to the communication cost are current algorithm;
Multiple currently stored amounts are combined according to the current algorithm and the pre- storage of separate unit central server,
Obtain current desired central server quantity;Multiple project level server letters are corresponded to according to the combined information of the currently stored amount
Breath, obtains the combined information of multiple project level servers;
According to current desired central server quantity and the combined information of polymorphic type project level server, to number is locally stored
According to being stored.
In a preferred embodiment, the polymorphic type project level server is additionally configured to from multiple community servers
Receive storage data.
In a preferred embodiment, the type of the local categorical data includes:Property data, finance data,
Medical data, home control data and agreement and director data.
In a preferred embodiment, the polymorphic type project level server is additionally configured to:
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm one respectively, and the is obtained according to the diversiform data communication cost
One total communication cost;
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use
Frequency obtains the communication cost of diversiform data by algorithm two respectively, and the is obtained according to the diversiform data communication cost
Two total communication costs.
In a preferred embodiment, polymorphic type project level server is additionally configured to:
Polymorphic type project level server described in poll deposits any two or the current of multiple polymorphic type project level servers
Reserves are combined, and capability value is less than and is combined closest to multiple item servers of separate unit central server after obtaining combination;
The quantity combined according to the multiple item server determines current desired central server quantity;Or;
According to genuinely convinced in default Current central number of servers, the currently stored amount of polymorphic type project level server and separate unit
The pre- storage of business device establishes tree data structure, is scanned for the structure and beta pruning, obtains capability value after combination and is less than and most
Multiple item servers close to separate unit central server combine;The quantity combined according to the multiple item server determines the
Two current desired central server quantity.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. the data efficient storage optimization method of extensive community, which is characterized in that this method implements the storage of multistage server
In structure, including,
Step S101:Polymorphic type project level server reports the currently stored amount and frequency of use of local categorical data;
Step S102:According to the pre- storage of separate unit central server, the currently stored amount of the local categorical data and described make
First total communication cost and second total communication cost are obtained by algorithm one and algorithm two respectively with frequency, it is logical according to this
Believe that the algorithm corresponding to the small value of cost is current algorithm;The algorithm one is Service Operation under the conditions of given number of servers
The optimization algorithm of the server storage of optimization, the algorithm two are the optimization algorithm of the server storage of Service Operation optimization;
Step S103:Multiple currently stored amounts are carried out according to the current algorithm and the pre- storage of separate unit central server
Combination, obtains current desired central server quantity;Multiple project level clothes are corresponded to according to the combined information of the currently stored amount
Business device information, obtains the combined information of multiple project level servers;
When current algorithm is algorithm two, the specific steps of the step S103 include:
Polymorphic type project level server described in poll, by any two or the currently stored amount of multiple polymorphic type project level servers
It is combined, capability value is less than and is combined closest to multiple item servers of separate unit central server after obtaining combination;According to
The quantity of the multiple item server combination determines current desired central server quantity;Or;
According to default Current central number of servers, the currently stored amount of polymorphic type project level server and separate unit central server
Pre- storage establish tree data structure, which is scanned for and beta pruning, obtains capability value after combination and be less than and closest
Multiple item servers of separate unit central server combine;The quantity combined according to the multiple item server determines that second works as
Central server quantity needed for preceding;
Step S104:According to current desired central server quantity and the combined information of polymorphic type project level server, to local
Storage data are stored.
2. the data efficient storage optimization method of extensive community according to claim 1, which is characterized in that in the step
Further include before rapid S101:
Step S100, the polymorphic type project level server receive storage data from multiple community servers.
3. the data efficient storage optimization method of extensive community according to claim 2, which is characterized in that the step
S101 includes,
It is described local categorical data type include:Property data, finance data, medical data, home control data and agreement
With director data.
4. the data efficient storage optimization method of extensive community according to claim 3, which is characterized in that the basis
The pre- storage of separate unit central server, the currently stored amount of the local categorical data and the frequency of use, pass through algorithm one
And algorithm two, it obtains first total communication cost respectively and the step of second total communication cost includes:
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use frequency
Rate obtains the communication cost of diversiform data respectively by algorithm one, and first is obtained according to the diversiform data communication cost
Total communication cost;
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use frequency
Rate obtains the communication cost of diversiform data respectively by algorithm two, and second is obtained according to the diversiform data communication cost
Total communication cost.
5. the data efficient storage optimization system of extensive community, which is characterized in that including, polymorphic type project level server, in
Central server and storage optimization processor;
The polymorphic type project level server reports the currently stored amount and frequency of use of local categorical data;
The polymorphic type project level server is deposited according to the pre- storage of separate unit central server, the current of local categorical data
Reserves and the frequency of use obtain first total communication cost and second total communication respectively by algorithm one and algorithm two
Cost, the algorithm corresponding to small value according to the communication cost are current algorithm;The algorithm one is given number of servers item
Under part, the optimization algorithm of the server storage of Service Operation optimization, the algorithm two is the server storage of Service Operation optimization
Optimization algorithm;
Multiple currently stored amounts are combined according to the current algorithm and the pre- storage of separate unit central server, are obtained
Current desired central server quantity;Multiple project level server infos are corresponded to according to the combined information of the currently stored amount,
Obtain the combined information of multiple project level servers;
When current algorithm is algorithm two, the polymorphic type project level server is additionally configured to:
Polymorphic type project level server described in poll, by any two or the currently stored amount of multiple polymorphic type project level servers
It is combined, capability value is less than and is combined closest to multiple item servers of separate unit central server after obtaining combination;According to
The quantity of the multiple item server combination determines current desired central server quantity;Or;
According to default Current central number of servers, the currently stored amount of polymorphic type project level server and separate unit central server
Pre- storage establish tree data structure, which is scanned for and beta pruning, obtains capability value after combination and be less than and closest
Multiple item servers of separate unit central server combine;The quantity combined according to the multiple item server determines that second works as
Central server quantity needed for preceding;
According to current desired central server quantity and the combined information of polymorphic type project level server, to be locally stored data into
Row storage.
6. the data efficient storage optimization system of extensive community according to claim 5, which is characterized in that the multiclass
Type project level server is additionally configured to receive storage data from multiple community servers.
7. the data efficient storage optimization system of extensive community according to claim 6, which is characterized in that the local
The type of categorical data includes:Property data, finance data, medical data, home control data and agreement and director data.
8. the data efficient storage optimization system of extensive community according to claim 7, which is characterized in that the multiclass
Type project level server is additionally configured to:
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use frequency
Rate obtains the communication cost of diversiform data respectively by algorithm one, and first is obtained according to the diversiform data communication cost
Total communication cost;
According to the pre- storage of separate unit central server, the currently stored amount of multiple local categorical datas and the use frequency
Rate obtains the communication cost of diversiform data respectively by algorithm two, and second is obtained according to the diversiform data communication cost
Total communication cost.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510273778.4A CN105049475B (en) | 2015-05-26 | 2015-05-26 | The data efficient storage optimization method and system of extensive community |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510273778.4A CN105049475B (en) | 2015-05-26 | 2015-05-26 | The data efficient storage optimization method and system of extensive community |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105049475A CN105049475A (en) | 2015-11-11 |
CN105049475B true CN105049475B (en) | 2018-10-30 |
Family
ID=54455678
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510273778.4A Active CN105049475B (en) | 2015-05-26 | 2015-05-26 | The data efficient storage optimization method and system of extensive community |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105049475B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105045527A (en) * | 2015-06-16 | 2015-11-11 | 重庆本原致创科技发展有限公司 | Optimization method and system for data storage of large-scale community |
CN105260127A (en) * | 2015-06-16 | 2016-01-20 | 重庆本原致创科技发展有限公司 | Efficient storage optimization method and system of data of large-scale community |
CN110019400B (en) * | 2017-12-25 | 2021-01-12 | 深圳云天励飞技术有限公司 | Data storage method, electronic device and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103037004A (en) * | 2012-12-21 | 2013-04-10 | 曙光信息产业(北京)有限公司 | Implement method and device of cloud storage system operation |
CN103744617A (en) * | 2013-12-20 | 2014-04-23 | 北京奇虎科技有限公司 | Merging and compressing method and device for data files in key-value storage system |
CN103763363A (en) * | 2014-01-14 | 2014-04-30 | 南京邮电大学 | Cloud storage system and file copy deployment method based on cloud storage system |
CN104536803A (en) * | 2014-12-23 | 2015-04-22 | 西安电子科技大学 | Virtual machine scheduling method based on combination optimization |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9329888B2 (en) * | 2013-01-28 | 2016-05-03 | International Business Machines Corporation | Computing optimized virtual machine allocations using equivalence combinations |
-
2015
- 2015-05-26 CN CN201510273778.4A patent/CN105049475B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103037004A (en) * | 2012-12-21 | 2013-04-10 | 曙光信息产业(北京)有限公司 | Implement method and device of cloud storage system operation |
CN103744617A (en) * | 2013-12-20 | 2014-04-23 | 北京奇虎科技有限公司 | Merging and compressing method and device for data files in key-value storage system |
CN103763363A (en) * | 2014-01-14 | 2014-04-30 | 南京邮电大学 | Cloud storage system and file copy deployment method based on cloud storage system |
CN104536803A (en) * | 2014-12-23 | 2015-04-22 | 西安电子科技大学 | Virtual machine scheduling method based on combination optimization |
Non-Patent Citations (2)
Title |
---|
Distributed Storage with Communication Costs;Craig Armstrong.etc;《Forty-Ninth Annual Allerton Conference Allerton House, UIUC, Illinois, USA》;20110930;全文 * |
云环境下的资源调度算法研究;范宗勤;《中国优秀硕士学位论文全文数据库》;20140615(第6期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN105049475A (en) | 2015-11-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109814951A (en) | The combined optimization method of task unloading and resource allocation in mobile edge calculations network | |
CN110287029A (en) | A method of it is adjusted based on kubernetes container resource dynamic | |
CN110162388A (en) | A kind of method for scheduling task, system and terminal device | |
CN103077082A (en) | Method and system for distributing data center load and saving energy during virtual machine migration | |
CN104484233B (en) | A kind of resource allocation methods | |
CN105049475B (en) | The data efficient storage optimization method and system of extensive community | |
CN107317712A (en) | A kind of creation method and device of network section | |
CN103841647A (en) | Multi-granularity telescopic packaging device and method based on base station resource pool | |
CN107026877A (en) | The method and apparatus that resource is managed in cloud platform | |
CN104144431B (en) | A kind of method, apparatus of mobile network's status predication and mobile network | |
CN107689982A (en) | Multi-data source method of data synchronization, application server and computer-readable recording medium | |
CN110149377A (en) | A kind of video service node resource allocation methods, system, device and storage medium | |
CN109195178A (en) | signal quality monitoring method and terminal device | |
CN111176840A (en) | Distributed task allocation optimization method and device, storage medium and electronic device | |
CN109358873A (en) | A kind of application program update method, storage medium and terminal device | |
CN103995749B (en) | The calculation task allocating method and system of cell cloud system | |
CN110167031B (en) | Resource allocation method, equipment and storage medium for centralized base station | |
CN103258389B (en) | The method of self-aided terminal upload file, system and self-aided terminal | |
CN106788932A (en) | Carrier aggregation method for optimizing configuration and device | |
CN104994136B (en) | The data store optimization method and system of extensive community | |
EP2797260A2 (en) | Risk mitigation in data center networks | |
CN115115144B (en) | Power market partitioning and clearing method, device, equipment and medium considering source load | |
CN110399534A (en) | Terminal capabilities report form generation method, device, equipment and storage medium | |
CN115981863A (en) | Intelligent cloud resource elastic expansion method and system combining business characteristics | |
CN115866059A (en) | Block chain link point scheduling method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 401120 Chongqing city Yubei District Longxi Street Road No. 6 are the first new irrigation station 9 building 12-15 Applicant after: CHONGQING FANGHUI TECHNOLOGY CO., LTD. Address before: 401120, Yubei District, Chongqing red street street 99, Huang Guandong and garden C1 building 13-4 Applicant before: CHONGQING FANGHUI TECHNOLOGY CO., LTD. |
|
CB02 | Change of applicant information | ||
CB03 | Change of inventor or designer information |
Inventor after: Guo Yajun Inventor before: Shu Haidong |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |