CN109347763A - A kind of data dispatching method based on length of data queue, apparatus and system - Google Patents
A kind of data dispatching method based on length of data queue, apparatus and system Download PDFInfo
- Publication number
- CN109347763A CN109347763A CN201811054783.6A CN201811054783A CN109347763A CN 109347763 A CN109347763 A CN 109347763A CN 201811054783 A CN201811054783 A CN 201811054783A CN 109347763 A CN109347763 A CN 109347763A
- Authority
- CN
- China
- Prior art keywords
- data
- virtual
- fringe node
- node
- queue
- 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
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a kind of data dispatching method based on length of data queue, system and devices, which comprises each destination node mended in structure determination network is opened up according to network, wherein destination node includes fringe node and terminal;According to preset schedule algorithm, the virtual data value of the corresponding data queue of each destination node is determined, wherein virtual data value is greater than 0;The virtual data value of the data queue of each destination node is set, so that total amount of data of each destination node by the sum of corresponding virtual data value and actual storage data volume as data queue, and data processing is carried out based on the total amount of data.Due to each destination node virtual data value and be not take up memory space, and the total amount of data of the sum of each network node virtual data value and actual storage data volume as data queue, just start upper one layer of transmission data to network when the data volume for being actually reached data does not meet threshold condition in this way, improves network operating efficiency.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of data dispatch side based on length of data queue
Method, apparatus and system.
Background technique
Due to the finiteness of Internet resources, such as network node computing capability, network link capacity, cause to deposit in network
In untreated or transmission data stacking, so as to cause network congestion.For this queuing network, generally use with each network section
The length of data queue of point is measurement, and data reduce the dispatching method that most fast gradient direction flows to length of data queue.By
It can be very good to adapt to the stochastic behaviour in network in the dispatching method, therefore be used widely, for example, applying in Internet of Things
In network.
It include generally data center, fringe node and terminal three-decker, bottom using the network architecture of above-mentioned dispatching method
Layer terminal receive or generate data, then by load shedding to fringe node, then by after fringe node collaborative process by remainder
It is focused on according to data center is passed to result.Each network node foundation has data queue, and data queue is based on data
Scheduling and processing result carry out dynamic change.Wherein, network node includes fringe node and terminal, and fringe node includes road
By, base station, wireless access point etc..
During processing, transmission of the data from terminal to data center needs the gesture of the data queue between network node
Difference, that is to say, that the difference of the data cumulant of terminal and the data cumulant of coupled fringe node needs to be more than certain
One threshold value can just be uploaded to coupled fringe node, likewise, the data cumulant of fringe node and coupled its
The difference of the data cumulant of his fringe node or data center needs to be more than a certain threshold value, can just be uploaded to data center or
It is sent to other fringe nodes.
Therefore, each network node, which needs a large amount of data stacking just, can guarantee effective operation of network, and terminal is as net
The bottom of network then needs most data accumulations.And the memory space of terminal is very limited, so will appear due to end
The problem of network operating efficiency caused by the memory space inadequate of end is low, and networking operational environment cannot be optimal.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of data dispatching method based on length of data queue, device and is
System solves the problems, such as that the network operating efficiency as caused by terminal storage space is insufficient is low to optimize networking operational environment.Specifically
Technical solution is as follows:
In a first aspect, the embodiment of the invention provides a kind of data dispatching method based on length of data queue, the side
Method includes:
Each destination node mended in structure determination network is opened up according to network, wherein the destination node includes fringe node
And terminal;
According to preset schedule algorithm, the virtual data value of the corresponding data queue of each destination node is determined, wherein institute
Virtual data value is stated greater than 0;
The virtual data value of the data queue of each destination node is set, so that each destination node will be corresponding
The total amount of data of the sum of virtual data value and actual storage data volume as data queue, and data are carried out based on the total amount of data
Processing.
Optionally, described according to preset schedule algorithm, determine the virtual number of the corresponding data queue of each destination node
The step of according to value, comprising:
According to preset schedule algorithm, the data handling queues of the fringe node and the virtual number of result storage queue are determined
According to value, and determine the virtual data value of the data handling queues of the terminal.
Optionally, described according to preset schedule algorithm, determine data handling queues and the result storage of the fringe node
The virtual data value of queue, and the step of determining the virtual data value of data handling queues of the terminal, comprising:
Data handling queues and the result storage queue that successive ignition calculates the fringe node are carried out according to following formula
Virtual data value and the terminal data handling queues virtual data value;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is net
The quantity of fringe node in network, R_ (j, 0) indicate the result storage for the fringe node j ∈ { 1,2...u } being connected with fringe node i
The virtual data value of queue, V are default control parameter, and G_ (i, j) indicates to transmit 1 bit data from fringe node i to edge section
The minimum transfer expense of point j, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_(i,
0) the virtual data value of the data handling queues of fringe node i is indicated, a expression obtains at fringe node i by data processing
Result data values and the data volume before processing ratio, Q_ (j, 0) indicate fringe node j virtual data value, p indicate
Cpu cycle number required for 1 bit data is handled, K (i) indicates the computing cost of fringe node i each cpu cycle, F (i) table
Show the computing capability of fringe node i;D_ (m, 0) indicates the data processing for the terminal m ∈ { 1,2...v } being connected with fringe node i
The virtual data value of queue, v are the quantity of terminal in network, and Z (m) indicates that the transport overhead of terminal m, Y (m, i) indicate eventually
The maximum link capacity of the link between m and fringe node i is held, T indicates the minimum system time.
Optionally, the method also includes:
Data center in network is determined as source node;
The virtual data value of the data handling queues and result storage queue that determine the source node is 0.
Second aspect, the embodiment of the invention provides a kind of data dispatch system based on length of data queue, the system
System includes:
Management equipment, for opening up each destination node mended in structure determination network according to network, according to preset schedule algorithm,
It determines the virtual data value of the corresponding data queue of each destination node, the void of the data queue of each destination node is set
Quasi- data value, wherein the destination node includes fringe node and terminal, and the virtual data value is greater than 0;
Terminal, for the total data by the sum of corresponding virtual data value and actual storage data volume as data queue
Amount, and data processing is carried out based on the total amount of data;
Fringe node, for by the sum of corresponding virtual data value and actual storage data volume as the total of data queue
Data volume, and data processing is carried out based on the total amount of data, and send processing result and/or pending data to data center;
Data center for receiving the processing result and/or the pending data, and carries out default processing.
Optionally, the management equipment is specifically used for according to preset schedule algorithm, at the data for determining the fringe node
The virtual data value of queue and result storage queue is managed, and determines the virtual data value of the data handling queues of the terminal.
Optionally, the management equipment is specifically used for carrying out the successive ignition calculating fringe node according to following formula
Data handling queues and result storage queue the virtual data value and terminal data handling queues virtual data
Value;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is net
The quantity of fringe node in network, R_ (j, 0) indicate the result storage for the fringe node j ∈ { 1,2...u } being connected with fringe node i
The virtual data value of queue, V are default control parameter, and G_ (i, j) indicates to transmit 1 bit data from fringe node i to edge section
The minimum transfer expense of point j, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_(i,
0) the virtual data value of the data handling queues of fringe node i is indicated, a expression obtains at fringe node i by data processing
Result data values and the data volume before processing ratio, Q_ (j, 0) indicate fringe node j virtual data value, p indicate
Cpu cycle number required for 1 bit data is handled, K (i) indicates the computing cost of fringe node i each cpu cycle, F (i) table
Show the computing capability of fringe node i;D_ (m, 0) indicates the data processing for the terminal m ∈ { 1,2...v } being connected with fringe node i
The virtual data value of queue, v are the quantity of terminal in network, and Z (m) indicates that the transport overhead of terminal m, Y (m, i) indicate eventually
The maximum link capacity of the link between m and fringe node i is held, T indicates the minimum system time.
Optionally, the terminal, specifically for by the conduct of the sum of corresponding virtual data value and actual storage data volume
The total amount of data of data handling queues, when the total data of the total amount of data and the data handling queues of coupled fringe node
When the difference of amount is greater than preset threshold, the data in data handling queues are uploaded to coupled fringe node;
The fringe node, the data uploaded specifically for obtaining coupled terminal, and by the data volume of the data
Total amount of data with the sum of corresponding virtual data value as data handling queues, and to the data in data handling queues into
Row processing obtains processing result, by the storage queue as a result of the sum of the data volume of processing result and corresponding virtual data value
Total amount of data, and the total amount of data based on data handling queues and the total amount of data of result storage queue upload data processing team
The processing result in data and/or result storage queue in column is to the data center.
Optionally, the management equipment is also used to the data center being determined as source node;Determine the source node
Data handling queues and the virtual data value of result storage queue are 0.
The third aspect, it is described the embodiment of the invention also provides a kind of data scheduling device based on length of data queue
Device includes:
Node determining module, for opening up each destination node mended in structure determination network according to network, wherein the purpose
Node includes fringe node and terminal;
Virtual data value determining module, for determining the corresponding data of each destination node according to preset schedule algorithm
The virtual data value of queue, wherein the virtual data value is greater than 0;
Virtual data value setup module, the virtual data value of the data queue for each destination node to be arranged, so that
Total amount of data of each destination node by the sum of corresponding virtual data value and actual storage data volume as data queue,
And data processing is carried out based on the total amount of data.
In scheme provided by the embodiment of the present invention, each purpose section mended in structure determination network is opened up according to network first
Point, wherein destination node includes fringe node and terminal;Then according to preset schedule algorithm, determine that each destination node is corresponding
The virtual data value of data queue, wherein virtual data value is greater than 0, then the virtual number of the data queue of each destination node is arranged
According to value, so that sum of each destination node by the sum of corresponding virtual data value and actual storage data volume as data queue
Data processing is carried out according to amount, and based on the total amount of data.Due to each destination node virtual data value and be not take up memory space,
Each destination node especially terminal can save a large amount of memory spaces to store the data being actually reached, and optimize network operation ring
Border, and the total amount of data of the sum of each network node virtual data value and actual storage data volume as data queue, exist in this way
It is actually reached when the difference of the data volume of data and the data cumulant of coupled destination node is not up to threshold value and just starts
To upper one layer of transmission data of network, network operating efficiency is improved.
Detailed description of the invention
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 technical 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
It obtains other drawings based on these drawings.
A kind of Fig. 1 net that the data dispatching method based on length of data queue is applicable provided by the embodiment of the present invention
Network topology diagram;
Fig. 2 is a kind of flow chart of the data dispatching method based on length of data queue provided by the embodiment of the present invention;
Fig. 3 is a kind of process of the method for determination of the corresponding virtual data amount of data center based on embodiment illustrated in fig. 2
Figure;
Fig. 4 is a kind of overall structure of the data dispatching method based on length of data queue based on embodiment illustrated in fig. 2
Schematic diagram;
Fig. 5 is a kind of structural representation of the data dispatch system based on length of data queue provided by the embodiment of the present invention
Figure;
Fig. 6 is a kind of structural representation of the data scheduling device based on length of data queue provided by the embodiment of the present invention
Figure;
Fig. 7 is a kind of structural schematic diagram of management equipment provided by the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In order to optimize networking operational environment, solve as terminal storage space it is insufficient caused by network operating efficiency is low asks
Topic, the embodiment of the invention provides a kind of data dispatching method based on length of data queue, device, system, controlling equipment and
Computer readable storage medium.
It is provided for the embodiments of the invention a kind of data dispatching method progress based on length of data queue first below
It introduces.
Data dispatching method based on length of data queue provided by embodiment to facilitate the understanding of the present invention, lower kept man of a noblewoman
First be provided for the embodiments of the invention the adaptable network of scheme open up mend structure be introduced.As shown in Figure 1, the network is opened up
Mending structure may include terminal 101, fringe node 102 and data center 103.Wherein, terminal 101 can for internet of things equipment,
Mobile phone etc., fringe node 102 may include base station, routing, wireless access point etc., and data center 103 is then progress data processing
Electronic equipment, can be not specifically limited herein for processor, server etc..
Terminal 101 is generally communicated to connect with unique fringe node, can be communicated to connect between each fringe node 102, phase
Data can be transmitted between mutually, fringe node 102 is all communicated to connect with data center 103.Data are provided in each terminal 101
Queue 104 is handled, for storing the data for itself generating or obtaining, when the sum of the data stored in data handling queues 104
When reaching a certain preset threshold according to amount, data can be uploaded to fringe node 102 connected to it by terminal 101.
Data handling queues 105 and result storage queue 106, received end are typically provided in fringe node 102
The data that end 101 uploads are stored in data handling queues 105, can be handled a portion data, and then
To data result, data result is stored in result storage queue 106, when the data handling queues 105 or knot of fringe node 102
It, can be by data result or untreated when the total amount of data of the data stored in fruit storage queue 106 is greater than a certain preset threshold
Data are uploaded to data center 103 and are further processed.
Based on above-mentioned network topology structure, in order to realize the scheduling of data processing in network, the embodiment of the present invention is provided
A kind of data dispatching method based on length of data queue can be applied to the management equipment in network, can for processor,
Computer, tablet computer etc., are not specifically limited herein.
As shown in Fig. 2, a kind of data dispatching method based on length of data queue, which comprises
S201 opens up each destination node mended in structure determination network according to network;
Wherein, the destination node includes fringe node and terminal.
S202 determines the virtual data value of the corresponding data queue of each destination node according to preset schedule algorithm;
Wherein, the virtual data value is greater than 0.
The virtual data value of the data queue of each destination node is arranged in S203, so that each destination node is by institute
The total amount of data of the sum of corresponding virtual data value and actual storage data volume as data queue, and based on the total amount of data into
Row data processing.
As it can be seen that each mesh mended in structure determination network is opened up according to network first in scheme provided by the embodiment of the present invention
Node, wherein destination node includes fringe node and terminal;Then according to preset schedule algorithm, each destination node pair is determined
The virtual data value for the data queue answered, wherein virtual data value is greater than 0, then the void of the data queue of each destination node is arranged
Quasi- data value, so that each destination node is by the sum of corresponding virtual data value and actual storage data volume as data queue
Total amount of data, and data processing is carried out based on the total amount of data.Due to each destination node virtual data value and be not take up storage
Space, each destination node especially terminal can save a large amount of memory spaces to store the data being actually reached, optimization network fortune
Row environment, and the total amount of data of the sum of each network node virtual data value and actual storage data volume as data queue, this
Sample when the difference of the data volume that is actually reached data and the data cumulant of coupled destination node is not up to threshold value just
Start upper one layer of transmission data to network, improves network operating efficiency.
In above-mentioned steps S201, in order to determine each destination node and its connection relationship in network, management equipment is first
Each destination node mended in structure determination network can be opened up according to network.Wherein, destination node may include terminal and edge section
Point.For example, as shown in Figure 1, management equipment can determine that the network opens up each destination node mended in the corresponding network of structure and is
16, including 6 terminals and 12 fringe nodes.
Next, management equipment can determine the corresponding data team of above-mentioned each destination node according to preset schedule algorithm
The virtual data value of column.Total amount of data in order to determine destination node is greater than the data volume of the data of actual storage, institute
It states virtual data value and is greater than 0.
Wherein, it should be noted that virtual data value is a numerical value, is not true data, and be not take up reality
Memory space.For example, virtual data value is 200,000,000, it is not the data that size is 200,000,000, and only a value is 200,000,000
Numerical value.In a kind of embodiment party, virtual data value can be indicated using placeholder.
In this way, the data queue of each destination node can be arranged after the virtual data value of the determining each destination node of management
Virtual data value.It should be noted that the virtual data value of each destination node may be the same or different, for its tool
Body numerical value management equipment can be determined according to factors such as real network topological structure and data class, be not specifically limited herein.
For example, management equipment determines that the virtual data value of terminal 101 shown in Fig. 1 is respectively 300 in step S202
Million, 350,000,000,380,000,000,450,000,000,500,000,000 and 580,000,000, then the void of the data queue of each terminal then can be set in management equipment
Quasi- data value is respectively 300,000,000,350,000,000,380,000,000,450,000,000,500,000,000 and 580,000,000.
The reality of management equipment can be arranged for so each destination node virtual data value and its data stored
The summation of data volume is as total amount of data, in turn, carries out data processing based on the total amount of data.As an example it is assumed that management is set
It is 300,000,000 for the virtual data value for being terminal A setting, the data volume of the data of actual storage is 260,000,000, then terminal A is just
The total amount of data that can determine itself is 560,000,000, if that the data handling queues of coupled fringe node B at this time
Total amount of data be 400,000,000, corresponding data threshold be 100,000,000, due to terminal A itself total amount of data and fringe node B this
When the differences of total amount of data of data handling queues be more than 100,000,000, so terminal A can upload data that it is stored to and its
Connected fringe node B.As it can be seen that the data volume of terminal A actual storage is much smaller than 400,000,000, using the scheme of the prior art
When will not upload data to fringe node B.
Data dispatching method provided in an embodiment of the present invention based on length of data queue increases data queue in network
Between potential difference, that is to say the difference between the total amount of data of each data queue, so that the data between each data queue are transmitted
Faster, more efficient, improve the whole work efficiency of network.
It is above-mentioned according to preset schedule algorithm as a kind of embodiment of the embodiment of the present invention, determine each purpose section
The step of virtual data value of the corresponding data queue of point, may include:
According to preset schedule algorithm, the data handling queues of the fringe node and the virtual number of result storage queue are determined
According to value, and determine the virtual data value of the data handling queues of the terminal.
Due in fringe node in addition to there are other than data handling queues, generally also there is result storage queue, so in order to
Further promote network operating efficiency, for fringe node, management equipment determine the virtual data value of its data handling queues with
Outside, the virtual data value of its result storage queue can also be determined, so that the data knot in the result storage queue of fringe node
Fruit also can be uploaded to as early as possible data center and be handled.
And for terminal, due to the limited storage space of terminal, data-handling capacity is also limited, so it is generally not
Data can be handled, also with regard to nonexistence results storage queue, then management equipment is only it needs to be determined that its data handling queues
Virtual data value.
As it can be seen that in the present embodiment, for terminal, management equipment is only it needs to be determined that the virtual data of its data handling queues
Value.For fringe node, management equipment is determined other than the virtual data value of its data handling queues, can also determine its knot
The virtual data value of fruit storage queue, in this way, the data result in the result storage queue of fringe node can be also uploaded to as early as possible
Data center is handled, and network operating efficiency is further increased.
Other than the virtual data value for determining the data handling queues of fringe node for above-mentioned management equipment, its knot is also determined
For the case where virtual data value of fruit storage queue, as a kind of embodiment of the embodiment of the present invention, above-mentioned basis is default
Dispatching algorithm determines the data handling queues of the fringe node and the virtual data value of result storage queue, and determines institute
The step of stating the virtual data value of the data handling queues of terminal may include:
Data handling queues and the result storage queue that successive ignition calculates the fringe node are carried out according to following formula
Virtual data value and the terminal data handling queues virtual data value.
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 } (1)
N_ (i, j)=V*G_ (i, j)-C_ (i, j) (2)
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 } (3)
H (i)=V*p*K (i)-F (i)/p (4)
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 } (5)
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T (6)
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is net
The quantity of fringe node in network, R_ (j, 0) indicate the result storage for the fringe node j ∈ { 1,2...u } being connected with fringe node i
The virtual data value of queue, V are default control parameter, and G_ (i, j) indicates to transmit 1 bit data from fringe node i to edge section
The minimum transfer expense of point j, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j.
V in formula (2) is default control parameter, and occurrence can be according to the data processing amount in practical application scene
Etc. factors determine, be not specifically limited herein.G_ (i, j) indicates to transmit 1 bit data from fringe node i to fringe node j's
Minimum transfer expense, C_ (i, j) indicate fringe node i and fringe node j between link maximum link capacity, G_ (i, j) and
The value of C_ (i, j) can be determined according to physical link situation.
It can be seen that can determine the result storage queue of each fringe node in network by above-mentioned formula (1) and formula (2)
Virtual data value.It is calculated for convenience, can be R_ (i, 0) and R_ (j, 0) default settings, such as can be 0,1,10
Deng.In this way, can be seen that R_ (i, 0) and R_ (j, 0) has coupled relation by formula (1) and formula (2), it is limited in progress in this way
After secondary iterative calculation, the value of R_ (i, 0) can tend to restrain, and can determine the value of R_ (i, 0) at this time.
Q_ (i, 0) in formula (3) indicates the virtual data value of the data handling queues of fringe node i, and a is indicated at edge
The data values of the result obtained at node i by data processing and the ratio of the data volume before processing, Q_ (j, 0) indicate edge
The virtual data value of node j, the p in formula (4) indicate CPU (Central Processing required for 1 bit data of processing
Unit, central processing unit) periodicity, the computing cost of K (i) expression fringe node i each cpu cycle, F (i) expression edge section
The computing capability of point i, unit can be CPU cycle of operation number per second.
Before a in formula (3) indicates data values and the processing of the result obtained at fringe node i by data processing
Data volume ratio, that is, data result after treatment data volume size account for handle before data size hundred
Divide ratio.
As it can be seen that can determine each side according to above-mentioned formula (3) and formula (4) after above-mentioned R_ (i, 0) is calculated
The virtual data value of the data handling queues of edge node.Likewise, calculated for convenience, can for Q_ (i, 0) and Q_ (j,
0) default settings, such as can be 0,1,10 etc..In this way, by formula (3) and formula (4) it can be seen that Q_ (i, 0) and Q_ (j,
0) there is coupled relation, in this way after the iterative calculation for carrying out limited times, the value of Q_ (i, 0) can tend to restrain, and at this time can
Determine the value of Q_ (i, 0).
D_ (m, 0) in formula (5) indicates the data handling queues for the terminal m ∈ { 1,2...v } being connected with fringe node i
Virtual data value, v is the quantity of terminal in network, and the Z (m) in formula (6) indicates the transport overhead of terminal m, Y (m, i) table
Show indicate terminal m and fringe node i between link maximum link capacity, T indicate the minimum system time, that is, every time into
The time scale that row system correlation updates.
As it can be seen that can be determined in network after above-mentioned Q_ (i, 0) is calculated by above-mentioned formula (5) and formula (6)
The virtual data value of the data handling queues of each terminal.
As it can be seen that in the present embodiment, each terminal in network can be calculated according to above-mentioned formula (1)-(6) in management equipment
And the corresponding virtual data value of each fringe node, it can rapidly and accurately determine each virtual data value.Also, due to above-mentioned formula
(1) factors such as real network link, expense are considered in-(6), so that being calculated by above-mentioned formula (1)-(6) virtual
Data value is more in line with the needs of actual scene, can farthest optimize networking operational environment, improves network operating efficiency.
As a kind of embodiment of the embodiment of the present invention, as shown in figure 3, the above method can also include:
Data center in network is determined as source node by S301;
The virtual data value of S302, the data handling queues and result storage queue that determine the source node are 0.
It is handled since all data in network finally can be uploaded to data center, management equipment can incite somebody to action
Data center in network is determined as source node, with corresponding with each destination node.
Further, it due to data center and without upper layer network structure, does not need data being uploaded to other yet
Equipment is handled, so its data handling queues and result storage queue actually do not need virtual data value, then
The data handling queues of source node and the virtual data value of result storage queue also can be determined as 0 by management equipment.
As it can be seen that in the present embodiment, due to data center and not having upper layer network structure, also not needing will be in data
It reaches other equipment to be handled, management equipment can be by the data handling queues of source node and the virtual number of result storage queue
It is determined as 0 according to value, to guarantee that data handling queues and the result storage queue of source node can store reality to the maximum extent
Data guarantee network operation state from another point of view, improve network operating efficiency.
Correspond to Fig. 4 below and is provided for the embodiments of the invention the progress of the data dispatching method based on length of data queue
Explanation.
Network topology structure shown in Fig. 4 includes management equipment, data center, 3 fringe nodes and multiple terminals, each end
End has data handling queues, and fringe node has data handling queues and result storage queue, and in each data queue
Virtual data value with management equipment setting, that is, part represented by figure bend.It should be noted that figure bend
The size in represented region is data volume representated by virtual data value, and is not its practical occupied data volume.
Terminal scheduling, unloading strategy and data processing in Fig. 4 indicate what fringe node or data center did data
Processing and transmission strategy, specific implementation are that the data dispatching method by above-mentioned based on length of data queue is real
It is existing, i.e., it is determined according to the potential difference between terminal, fringe node and the data queue of data center.
As it can be seen that the sum of virtual data value and actual storage data volume in data handling queues in each terminal with
When the difference of the total amount of data of the data handling queues of its connected fringe node is greater than its corresponding preset threshold, terminal will
Data are uploaded to corresponding fringe node.Likewise, virtual data value and reality in data handling queues in fringe node
The sum of virtual data value in result storage queue and actual storage data volume in the sum of storage data quantity and fringe node
When meeting corresponding potential difference condition, fringe node will upload untreatment data and/or data result to other fringe nodes or
Data center.
Wherein, the sum of the virtual data value in the result storage queue in fringe node and actual storage data volume satisfaction pair
When the potential difference condition answered, fringe node uploads untreatment data and/or data result to other fringe nodes or data center
Concrete mode can be realized using mode in the prior art, be not specifically limited and illustrated herein.
It should be noted that the data handling queues in a fringe node and result storage queue are merely illustrated in Fig. 4,
It is not intended that other fringe nodes do not have data handling queues and result storage queue, each of network edge section
Point all has data handling queues and result storage queue, and management equipment can be the data processing of each fringe node
Virtual data value is arranged in queue and result storage queue.
Corresponding to the above-mentioned data dispatching method based on length of data queue, the embodiment of the invention also provides one kind to be based on
The data dispatch system of length of data queue.
A kind of data dispatch system based on length of data queue is provided for the embodiments of the invention below to be introduced.
As shown in figure 5, a kind of data dispatch system based on length of data queue, the system comprises:
Management equipment 510 is calculated for opening up each destination node mended in structure determination network according to network according to preset schedule
Method determines the virtual data value of the corresponding data queue of each destination node, and the data queue of each destination node is arranged
Virtual data value;
Wherein, the destination node includes fringe node and terminal, and the virtual data value is greater than 0.
Terminal 520, for by the sum of corresponding virtual data value and actual storage data volume as the total of data queue
Data volume, and data processing is carried out based on the total amount of data;
Fringe node 530, for regarding the sum of corresponding virtual data value and actual storage data volume as data queue
Total amount of data, and data processing is carried out based on the total amount of data, and sends processing result and/or pending data into data
The heart;
Data center 540 for receiving the processing result and/or the pending data, and carries out default processing.
As it can be seen that management equipment can be opened up according to network mends structure determination network in scheme provided by the embodiment of the present invention
In each destination node, wherein destination node includes fringe node and terminal;Then according to preset schedule algorithm, each mesh is determined
The corresponding data queue of node virtual data value, wherein virtual data value is greater than 0, then the data of each destination node is arranged
The virtual data value of queue, terminal can regard the sum of corresponding virtual data value and actual storage data volume as data queue
Total amount of data, and based on the total amount of data carry out data processing.Fringe node can be by corresponding virtual data value and reality
Total amount of data of the sum of the border storage data quantity as data queue, and data processing is carried out based on the total amount of data, and at transmission
Result and/or pending data are managed to data center.Data center can receive processing result and/or pending data, go forward side by side
The default processing of row.Due to each terminal and the virtual data value of fringe node and it is not take up memory space, each destination node is especially
Terminal can save a large amount of memory spaces to store the data being actually reached, and optimize networking operational environment, and each network node
The total amount of data of the sum of virtual data value and actual storage data volume as data queue, in this way in the data for being actually reached data
The difference of amount and the data cumulant of coupled destination node just starts upper one layer of transmission to network when being not up to threshold value
Data improve network operating efficiency.
As a kind of embodiment of the embodiment of the present invention, above-mentioned management equipment 510 specifically can be used for being adjusted according to default
Algorithm is spent, determines the data handling queues of the fringe node and the virtual data value of result storage queue, and described in determination
The virtual data value of the data handling queues of terminal.
As a kind of embodiment of the embodiment of the present invention, above-mentioned management equipment 510 specifically can be used for according to following public affairs
Formula carries out successive ignition and calculates the data handling queues of the fringe node and the virtual data value of result storage queue, Yi Jisuo
State the virtual data value of the data handling queues of terminal;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is net
The quantity of fringe node in network, R_ (j, 0) indicate the result storage for the fringe node j ∈ { 1,2...u } being connected with fringe node i
The virtual data value of queue, V are default control parameter, and G_ (i, j) indicates to transmit 1 bit data from fringe node i to edge section
The minimum transfer expense of point j, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_(i,
0) the virtual data value of the data handling queues of fringe node i is indicated, a expression obtains at fringe node i by data processing
Result data values and the data volume before processing ratio, Q_ (j, 0) indicate fringe node j virtual data value, p indicate
Cpu cycle number required for 1 bit data is handled, K (i) indicates the computing cost of fringe node i each cpu cycle, F (i) table
Show the computing capability of fringe node i;D_ (m, 0) indicates the data processing for the terminal m ∈ { 1,2...v } being connected with fringe node i
The virtual data value of queue, v are the quantity of terminal in network, and Z (m) indicates that the transport overhead of terminal m, Y (m, i) indicate eventually
The maximum link capacity of the link between m and fringe node i is held, T indicates the minimum system time.
As a kind of embodiment of the embodiment of the present invention, above-mentioned terminal 520, specifically can be used for will be corresponding virtual
The total amount of data of the sum of data value and actual storage data volume as data handling queues, when the total amount of data and coupled
When the difference of the total amount of data of the data handling queues of fringe node is greater than preset threshold, the data in data handling queues are uploaded
To coupled fringe node 530;
Above-mentioned fringe node 530, specifically can be used for obtaining the data that coupled terminal 520 uploads, and by the number
According to total amount of data as data handling queues of data volume and the sum of corresponding virtual data value, and to data handling queues
In data handled to obtain processing result, as a result by the sum of the data volume of processing result and corresponding virtual data value
The total amount of data of storage queue, and the total amount of data based on data handling queues and the total amount of data of result storage queue upload
The processing result in data and/or result storage queue in data handling queues is to the data center 540.
Above-mentioned preset threshold can determine according to the practical factors such as memory space of physical end, fringe node, herein not
It is specifically limited.
As a kind of embodiment of the embodiment of the present invention, above-mentioned management equipment 510, can be also used for will be in the data
The heart 540 is determined as source node;The virtual data value of the data handling queues and result storage queue that determine the source node is
0。
Corresponding to the above-mentioned data dispatching method based on length of data queue, the embodiment of the invention also provides one kind to be based on
The data scheduling device of length of data queue.
A kind of data scheduling device based on length of data queue is provided for the embodiments of the invention below to be introduced.
As shown in fig. 6, a kind of data scheduling device based on length of data queue, described device include:
Node determining module 610, for opening up each destination node mended in structure determination network according to network;
Wherein, the destination node includes fringe node and terminal.
Virtual data value determining module 620, for determining the corresponding number of each destination node according to preset schedule algorithm
According to the virtual data value of queue;
Wherein, the virtual data value is greater than 0.
Virtual data value setup module 630, the virtual data value of the data queue for each destination node to be arranged, with
Make total data of each destination node by the sum of corresponding virtual data value and actual storage data volume as data queue
Amount, and data processing is carried out based on the total amount of data.
As it can be seen that each mesh mended in structure determination network is opened up according to network first in scheme provided by the embodiment of the present invention
Node, wherein destination node includes fringe node and terminal;Then according to preset schedule algorithm, each destination node pair is determined
The virtual data value for the data queue answered, wherein virtual data value is greater than 0, then the void of the data queue of each destination node is arranged
Quasi- data value, so that each destination node is by the sum of corresponding virtual data value and actual storage data volume as data queue
Total amount of data, and data processing is carried out based on the total amount of data.Due to each destination node virtual data value and be not take up storage
Space, each destination node especially terminal can save a large amount of memory spaces to store the data being actually reached, optimization network fortune
Row environment, and the total amount of data of the sum of each network node virtual data value and actual storage data volume as data queue, this
Sample when the difference of the data volume that is actually reached data and the data cumulant of coupled destination node is not up to threshold value just
Start upper one layer of transmission data to network, improves network operating efficiency.
As a kind of embodiment of the embodiment of the present invention, above-mentioned virtual data value determining module 620 may include:
Virtual data value determination unit (being not shown in Fig. 6), for determining the fringe node according to preset schedule algorithm
Data handling queues and result storage queue virtual data value, and determine the terminal data handling queues it is virtual
Data value.
As a kind of embodiment of the embodiment of the present invention, above-mentioned virtual data value determination unit may include:
Virtual data value determines subelement (being not shown in Fig. 6), calculates institute for carrying out successive ignition according to following formula
State the data handling queues of the data handling queues of fringe node and the virtual data value of result storage queue and the terminal
Virtual data value;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is net
The quantity of fringe node in network, R_ (j, 0) indicate the result storage for the fringe node j ∈ { 1,2...u } being connected with fringe node i
The virtual data value of queue, V are default control parameter, and G_ (i, j) indicates to transmit 1 bit data from fringe node i to edge section
The minimum transfer expense of point j, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_(i,
0) the virtual data value of the data handling queues of fringe node i is indicated, a expression obtains at fringe node i by data processing
Result data values and the data volume before processing ratio, Q_ (j, 0) indicate fringe node j virtual data value, p indicate
Cpu cycle number required for 1 bit data is handled, K (i) indicates the computing cost of fringe node i each cpu cycle, F (i) table
Show the computing capability of fringe node i;D_ (m, 0) indicates the data processing for the terminal m ∈ { 1,2...v } being connected with fringe node i
The virtual data value of queue, v are the quantity of terminal in network, and Z (m) indicates that the transport overhead of terminal m, Y (m, i) indicate eventually
The maximum link capacity of the link between m and fringe node i is held, T indicates the minimum system time.
As a kind of embodiment of the embodiment of the present invention, above-mentioned apparatus can also include:
Source node determining module (is not shown) in Fig. 6, for the data center in network to be determined as source node;
Source node virtual data value determining module (being not shown in Fig. 6), for determining the data processing team of the source node
Column and the virtual data value of result storage queue are 0.
The embodiment of the invention also provides a kind of management equipments, as shown in fig. 7, controller may include processor 701, lead to
Believe interface 702, memory 703 and communication bus 704, wherein processor 701, communication interface 702, memory 703 pass through communication
Bus 704 completes mutual communication,
Memory 703, for storing computer program;
Processor 701 when for executing the program stored on memory 703, realizes following steps:
Each destination node mended in structure determination network is opened up according to network;
Wherein, the destination node includes fringe node and terminal.
According to preset schedule algorithm, the virtual data value of the corresponding data queue of each destination node is determined;
Wherein, the virtual data value is greater than 0.
The virtual data value of the data queue of each destination node is set, so that each destination node will be corresponding
The total amount of data of the sum of virtual data value and actual storage data volume as data queue, and data are carried out based on the total amount of data
Processing.
As it can be seen that management equipment opens up according to network mend structure determination network first in scheme provided by the embodiment of the present invention
In each destination node, wherein destination node includes fringe node and terminal;Then according to preset schedule algorithm, each mesh is determined
The corresponding data queue of node virtual data value, wherein virtual data value is greater than 0, then the data of each destination node is arranged
The virtual data value of queue, so that each destination node regard the sum of corresponding virtual data value and actual storage data volume as number
Data processing is carried out according to the total amount of data of queue, and based on the total amount of data.Due to each destination node virtual data value not
Memory space is occupied, each destination node especially terminal can save a large amount of memory spaces to store the data being actually reached, excellent
Change networking operational environment, and the sum of the sum of each network node virtual data value and actual storage data volume as data queue
According to amount, threshold is not up in the difference of the data cumulant of the data volume and coupled destination node that are actually reached data in this way
Just start upper one layer of transmission data to network when value, improve network operating efficiency.
The communication bus that above-mentioned management equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.
Communication interface is for the communication between above-mentioned management equipment and other equipment.
Memory may include random access memory (Random Access Memory, RAM), also may include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
CPU), network processing unit (Network Processor, NP) etc.;It can also be digital signal processor (Digital Signal
Processing, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components.
Wherein, above-mentioned according to preset schedule algorithm, determine the virtual data of the corresponding data queue of each destination node
The step of value may include:
According to preset schedule algorithm, the data handling queues of the fringe node and the virtual number of result storage queue are determined
According to value, and determine the virtual data value of the data handling queues of the terminal.
Wherein, above-mentioned according to preset schedule algorithm, determine data handling queues and the result storage team of the fringe node
The virtual data value of column, and the step of determining the virtual data value of data handling queues of the terminal may include:
Data handling queues and the result storage queue that successive ignition calculates the fringe node are carried out according to following formula
Virtual data value and the terminal data handling queues virtual data value;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is net
The quantity of fringe node in network, R_ (j, 0) indicate the result storage for the fringe node j ∈ { 1,2...u } being connected with fringe node i
The virtual data value of queue, V are default control parameter, and G_ (i, j) indicates to transmit 1 bit data from fringe node i to edge section
The minimum transfer expense of point j, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_(i,
0) the virtual data value of the data handling queues of fringe node i is indicated, a expression obtains at fringe node i by data processing
Result data values and the data volume before processing ratio, Q_ (j, 0) indicate fringe node j virtual data value, p indicate
Cpu cycle number required for 1 bit data is handled, K (i) indicates the computing cost of fringe node i each cpu cycle, F (i) table
Show the computing capability of fringe node i;D_ (m, 0) indicates the data processing for the terminal m ∈ { 1,2...v } being connected with fringe node i
The virtual data value of queue, v are the quantity of terminal in network, and Z (m) indicates that the transport overhead of terminal m, Y (m, i) indicate eventually
The maximum link capacity of the link between m and fringe node i is held, T indicates the minimum system time.
Wherein, the above method can also include:
Data center in network is determined as source node;
The virtual data value of the data handling queues and result storage queue that determine the source node is 0.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer readable storage medium memory
Computer program is contained, the computer program performs the steps of when being executed by processor
Each destination node mended in structure determination network is opened up according to network;
Wherein, the destination node includes fringe node and terminal.
According to preset schedule algorithm, the virtual data value of the corresponding data queue of each destination node is determined;
Wherein, the virtual data value is greater than 0.
The virtual data value of the data queue of each destination node is set, so that each destination node will be corresponding
The total amount of data of the sum of virtual data value and actual storage data volume as data queue, and data are carried out based on the total amount of data
Processing.
As it can be seen that in scheme provided by the embodiment of the present invention, when computer program is executed by processor, first according to network
Open up each destination node mended in structure determination network, wherein destination node includes fringe node and terminal;Then it is adjusted according to default
Algorithm is spent, determines the virtual data value of the corresponding data queue of each destination node, wherein virtual data value is greater than 0, then is arranged each
The virtual data value of the data queue of destination node, so that each destination node is by corresponding virtual data value and actual storage number
Total amount of data according to the sum of amount as data queue, and data processing is carried out based on the total amount of data.Due to each destination node
Virtual data value is simultaneously not take up memory space, and each destination node especially terminal can save a large amount of memory spaces to store reality
The data of arrival optimize networking operational environment, and the conduct of the sum of each network node virtual data value and actual storage data volume
The total amount of data of data queue, in this way the data cumulant in the data volume and coupled destination node that are actually reached data
Difference just start upper one layer of transmission data to network when being not up to threshold value, improve network operating efficiency.
Wherein, above-mentioned according to preset schedule algorithm, determine the virtual data of the corresponding data queue of each destination node
The step of value may include:
According to preset schedule algorithm, the data handling queues of the fringe node and the virtual number of result storage queue are determined
According to value, and determine the virtual data value of the data handling queues of the terminal.
Wherein, above-mentioned according to preset schedule algorithm, determine data handling queues and the result storage team of the fringe node
The virtual data value of column, and the step of determining the virtual data value of data handling queues of the terminal may include:
Data handling queues and the result storage queue that successive ignition calculates the fringe node are carried out according to following formula
Virtual data value and the terminal data handling queues virtual data value;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is net
The quantity of fringe node in network, R_ (j, 0) indicate the result storage for the fringe node j ∈ { 1,2...u } being connected with fringe node i
The virtual data value of queue, V are default control parameter, and G_ (i, j) indicates to transmit 1 bit data from fringe node i to edge section
The minimum transfer expense of point j, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_(i,
0) the virtual data value of the data handling queues of fringe node i is indicated, a expression obtains at fringe node i by data processing
Result data values and the data volume before processing ratio, Q_ (j, 0) indicate fringe node j virtual data value, p indicate
Cpu cycle number required for 1 bit data is handled, K (i) indicates the computing cost of fringe node i each cpu cycle, F (i) table
Show the computing capability of fringe node i;D_ (m, 0) indicates the data processing for the terminal m ∈ { 1,2...v } being connected with fringe node i
The virtual data value of queue, v are the quantity of terminal in network, and Z (m) indicates that the transport overhead of terminal m, Y (m, i) indicate eventually
The maximum link capacity of the link between m and fringe node i is held, T indicates the minimum system time.
Wherein, the above method can also include:
Data center in network is determined as source node;
The virtual data value of the data handling queues and result storage queue that determine the source node is 0.
It should be noted that for above system, device, management equipment and computer readable storage medium embodiment and
Speech, since it is substantially similar to the method embodiment, so being described relatively simple, referring to the part of embodiment of the method in place of correlation
Explanation.
Need further exist for explanation, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (10)
1. a kind of data dispatching method based on length of data queue, which is characterized in that the described method includes:
Each destination node mended in structure determination network is opened up according to network, wherein the destination node includes fringe node and end
End;
According to preset schedule algorithm, the virtual data value of the corresponding data queue of each destination node is determined, wherein the void
Quasi- data value is greater than 0;
The virtual data value of the data queue of each destination node is set, so that each destination node will be corresponding virtual
The total amount of data of the sum of data value and actual storage data volume as data queue, and carried out at data based on the total amount of data
Reason.
2. the method as described in claim 1, which is characterized in that it is described according to preset schedule algorithm, determine each purpose section
The step of virtual data value of the corresponding data queue of point, comprising:
According to preset schedule algorithm, the data handling queues of the fringe node and the virtual data of result storage queue are determined
Value, and determine the virtual data value of the data handling queues of the terminal.
3. method according to claim 2, which is characterized in that it is described according to preset schedule algorithm, determine the fringe node
Data handling queues and result storage queue virtual data value, and determine the terminal data handling queues it is virtual
The step of data value, comprising:
Successive ignition, which is carried out, according to following formula calculates the data handling queues of the fringe node and the void of result storage queue
The virtual data value of quasi- data value and the data handling queues of the terminal;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is in network
The quantity of fringe node, R_ (j, 0) indicate the result storage queue for the fringe node j ∈ { 1,2...u } being connected with fringe node i
Virtual data value, V be default control parameter, G_ (i, j) indicate from fringe node i transmit 1 bit data to fringe node j's
Minimum transfer expense, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_ (i, 0) table
Show the virtual data value of the data handling queues of fringe node i, a indicates the knot obtained at fringe node i by data processing
The data values of fruit and the ratio of the data volume before processing, Q_ (j, 0) indicate the virtual data value of fringe node j, p expression processing
Cpu cycle number required for 1 bit data, K (i) indicate that the computing cost of fringe node i each cpu cycle, F (i) indicate side
The computing capability of edge node i;D_ (m, 0) indicates the data handling queues for the terminal m ∈ { 1,2...v } being connected with fringe node i
Virtual data value, v be network in terminal quantity, Z (m) indicate terminal m transport overhead, Y (m, i) indicate indicate terminal m
The maximum link capacity of link between fringe node i, T indicate the minimum system time.
4. the method according to claim 1, which is characterized in that the method also includes:
Data center in network is determined as source node;
The virtual data value of the data handling queues and result storage queue that determine the source node is 0.
5. a kind of data dispatch system based on length of data queue, which is characterized in that the system comprises:
Management equipment, according to preset schedule algorithm, is determined for opening up each destination node mended in structure determination network according to network
The virtual data value of the corresponding data queue of each destination node, is arranged the virtual number of the data queue of each destination node
According to value, wherein the destination node includes fringe node and terminal, and the virtual data value is greater than 0;
Terminal, for the total amount of data by the sum of corresponding virtual data value and actual storage data volume as data queue,
And data processing is carried out based on the total amount of data;
Fringe node, for the total data by the sum of corresponding virtual data value and actual storage data volume as data queue
Amount, and data processing is carried out based on the total amount of data, and send processing result and/or pending data to data center;
Data center for receiving the processing result and/or the pending data, and carries out default processing.
6. system as claimed in claim 5, which is characterized in that
The management equipment is specifically used for determining the data handling queues and knot of the fringe node according to preset schedule algorithm
The virtual data value of fruit storage queue, and determine the virtual data value of the data handling queues of the terminal.
7. system as claimed in claim 5, which is characterized in that
The management equipment, specifically for carrying out the data processing team that successive ignition calculates the fringe node according to following formula
The virtual data value of column and the data handling queues of the virtual data value and terminal of result storage queue;
R_ (i, 0)=max { min_j { R_ (j, 0)+N_ (i, j) }, 0 };
N_ (i, j)=V*G_ (i, j)-C_ (i, j);
Q_ (i, 0)=max { min_j { a*R_ (i, 0)+H (i), Q_ (j, 0)+N (i, j) }, 0 };
H (i)=V*p*K (i)-F (i)/p;
D_ (m, 0)=max { Q_ (i, 0)+S (m), 0 };
S (m)=V*Z (m)/Y (m, i)-Y (m, i) * T;
Wherein, R_ (i, 0) indicates the virtual data value of the result storage queue of fringe node i ∈ { 1,2...u }, and u is in network
The quantity of fringe node, R_ (j, 0) indicate the result storage queue for the fringe node j ∈ { 1,2...u } being connected with fringe node i
Virtual data value, V be default control parameter, G_ (i, j) indicate from fringe node i transmit 1 bit data to fringe node j's
Minimum transfer expense, C_ (i, j) indicate the maximum link capacity of link between fringe node i and fringe node j;Q_ (i, 0) table
Show the virtual data value of the data handling queues of fringe node i, a indicates the knot obtained at fringe node i by data processing
The data values of fruit and the ratio of the data volume before processing, Q_ (j, 0) indicate the virtual data value of fringe node j, p expression processing
Cpu cycle number required for 1 bit data, K (i) indicate that the computing cost of fringe node i each cpu cycle, F (i) indicate side
The computing capability of edge node i;D_ (m, 0) indicates the data handling queues for the terminal m ∈ { 1,2...v } being connected with fringe node i
Virtual data value, v be network in terminal quantity, Z (m) indicate terminal m transport overhead, Y (m, i) indicate indicate terminal m
The maximum link capacity of link between fringe node i, T indicate the minimum system time.
8. system as claimed in claim 7, which is characterized in that
The terminal, specifically for regarding the sum of corresponding virtual data value and actual storage data volume as data handling queues
Total amount of data, when the difference of the total amount of data and the total amount of data of the data handling queues of coupled fringe node is greater than
When preset threshold, the data in data handling queues are uploaded to coupled fringe node;
The fringe node, the data uploaded specifically for obtaining coupled terminal, and by the data volume of the data and institute
Total amount of data of the sum of the corresponding virtual data value as data handling queues, and to the data in data handling queues at
Reason obtains processing result, by the sum of the sum of the data volume of processing result and corresponding virtual data value storage queue as a result
The total amount of data of total amount of data and result storage queue according to amount, and based on data handling queues uploads in data handling queues
Data and/or result storage queue in processing result to the data center.
9. such as the described in any item systems of claim 5-8, which is characterized in that
The management equipment is also used to the data center being determined as source node;Determine the data processing team of the source node
Column and the virtual data value of result storage queue are 0.
10. a kind of data scheduling device based on length of data queue, which is characterized in that described device includes:
Node determining module, for opening up each destination node mended in structure determination network according to network, wherein the destination node
Including fringe node and terminal;
Virtual data value determining module, for determining the corresponding data queue of each destination node according to preset schedule algorithm
Virtual data value, wherein the virtual data value be greater than 0;
Virtual data value setup module, the virtual data value of the data queue for each destination node to be arranged, so that described
Total amount of data of each destination node by the sum of corresponding virtual data value and actual storage data volume as data queue, and base
Data processing is carried out in the total amount of data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811054783.6A CN109347763B (en) | 2018-09-11 | 2018-09-11 | Data scheduling method, device and system based on data queue length |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811054783.6A CN109347763B (en) | 2018-09-11 | 2018-09-11 | Data scheduling method, device and system based on data queue length |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109347763A true CN109347763A (en) | 2019-02-15 |
CN109347763B CN109347763B (en) | 2021-11-05 |
Family
ID=65304860
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811054783.6A Active CN109347763B (en) | 2018-09-11 | 2018-09-11 | Data scheduling method, device and system based on data queue length |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109347763B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109981487A (en) * | 2019-03-27 | 2019-07-05 | 北京邮电大学 | A kind of data dispatching method, device, electronic equipment and readable storage medium storing program for executing |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1805308A (en) * | 2005-01-12 | 2006-07-19 | 日本电气株式会社 | Radio packet signal transmission system, radio packet signal transmission terminal and radio packet signal transmission method used in these |
EP1696339A2 (en) * | 2005-02-25 | 2006-08-30 | Microsoft Corporation | System and method for testing data format using targeted variant input |
CN102630378A (en) * | 2009-11-25 | 2012-08-08 | 瑞典爱立信有限公司 | Individualized data communication on the basis of a descriptive file |
CN102740467A (en) * | 2011-04-02 | 2012-10-17 | 华为技术有限公司 | Uplink feedback method of high speed dedicated physical control channel (HS-DPCCH), terminal and base station thereof |
CN103188801A (en) * | 2011-12-29 | 2013-07-03 | 中兴通讯股份有限公司 | Control method and control device of station (STA) |
CN104066122A (en) * | 2014-07-09 | 2014-09-24 | 东南大学 | Congestion control and transmission scheduling method for cellular and D2D hybrid network |
WO2016020726A1 (en) * | 2014-08-07 | 2016-02-11 | Telefonaktiebolaget L M Ericsson (Publ) | Data transfer in a system of connected things |
CN105573662A (en) * | 2014-10-31 | 2016-05-11 | 群联电子股份有限公司 | Data writing method, storage control circuit unit and storage storing device |
CN105872003A (en) * | 2015-12-21 | 2016-08-17 | 乐视云计算有限公司 | Data processing method, device and system based on P2P (Peer-to-Peer) network |
CN106612335A (en) * | 2017-02-07 | 2017-05-03 | 济南浪潮高新科技投资发展有限公司 | Method of adopting Docker container to realize IoT (Internet of things) information exchange and communication |
CN108959313A (en) * | 2017-05-23 | 2018-12-07 | 中国移动通信集团重庆有限公司 | Concurrent processing method, device and storage medium towards mass small documents |
-
2018
- 2018-09-11 CN CN201811054783.6A patent/CN109347763B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1805308A (en) * | 2005-01-12 | 2006-07-19 | 日本电气株式会社 | Radio packet signal transmission system, radio packet signal transmission terminal and radio packet signal transmission method used in these |
EP1696339A2 (en) * | 2005-02-25 | 2006-08-30 | Microsoft Corporation | System and method for testing data format using targeted variant input |
CN102630378A (en) * | 2009-11-25 | 2012-08-08 | 瑞典爱立信有限公司 | Individualized data communication on the basis of a descriptive file |
CN102740467A (en) * | 2011-04-02 | 2012-10-17 | 华为技术有限公司 | Uplink feedback method of high speed dedicated physical control channel (HS-DPCCH), terminal and base station thereof |
CN103188801A (en) * | 2011-12-29 | 2013-07-03 | 中兴通讯股份有限公司 | Control method and control device of station (STA) |
CN104066122A (en) * | 2014-07-09 | 2014-09-24 | 东南大学 | Congestion control and transmission scheduling method for cellular and D2D hybrid network |
WO2016020726A1 (en) * | 2014-08-07 | 2016-02-11 | Telefonaktiebolaget L M Ericsson (Publ) | Data transfer in a system of connected things |
CN105573662A (en) * | 2014-10-31 | 2016-05-11 | 群联电子股份有限公司 | Data writing method, storage control circuit unit and storage storing device |
CN105872003A (en) * | 2015-12-21 | 2016-08-17 | 乐视云计算有限公司 | Data processing method, device and system based on P2P (Peer-to-Peer) network |
CN106612335A (en) * | 2017-02-07 | 2017-05-03 | 济南浪潮高新科技投资发展有限公司 | Method of adopting Docker container to realize IoT (Internet of things) information exchange and communication |
CN108959313A (en) * | 2017-05-23 | 2018-12-07 | 中国移动通信集团重庆有限公司 | Concurrent processing method, device and storage medium towards mass small documents |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109981487A (en) * | 2019-03-27 | 2019-07-05 | 北京邮电大学 | A kind of data dispatching method, device, electronic equipment and readable storage medium storing program for executing |
CN109981487B (en) * | 2019-03-27 | 2020-10-27 | 北京邮电大学 | Data scheduling method and device, electronic equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109347763B (en) | 2021-11-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107888425B (en) | network slice deployment method and device for mobile communication system | |
CN104901989B (en) | A kind of Site Service offer system and method | |
CN108027789A (en) | The service quality of interconnection piece with multistage arbitration | |
CN107404541A (en) | A kind of method and system of peer-to-peer network transmission neighbor node selection | |
CN114253735B (en) | Task processing method and device and related equipment | |
CN106934027A (en) | Distributed reptile realization method and system | |
CN105871739A (en) | Method for processing messages and computing equipment | |
CN109147788A (en) | The update method and device in local voice library | |
CN110519370A (en) | A kind of edge calculations resource allocation methods based on Facility Location Problem | |
CN108696911A (en) | A kind of selection method and device of data transmission of internet of things mode | |
CN112464150A (en) | Method, device and medium for realizing data convolution operation based on FPGA | |
CN107454136B (en) | Calculation unloading method and device based on end-to-end P2P and control equipment | |
CN115563674A (en) | Initial floorplan generation method and apparatus, electronic device, and storage medium | |
CN109347763A (en) | A kind of data dispatching method based on length of data queue, apparatus and system | |
CN112256413A (en) | Scheduling method and device for edge computing task based on Internet of things | |
CN108924203A (en) | Data copy self-adapting distribution method, distributed computing system and relevant device | |
TWI792784B (en) | Method and system for federated reinforcement learning based offloading optimization in edge computing | |
CN107547429A (en) | One kind load determines method, apparatus and electronic equipment | |
TWI665932B (en) | Group host selection method for device-to-device network and control platform for selecting group host | |
CN113472591A (en) | Method and device for determining service performance | |
CN107679233A (en) | Distributed reptile method for allocating tasks and system | |
CN112529235A (en) | Path determining method and device, electronic equipment and computer readable storage medium | |
CN106161068A (en) | A kind of recovery prompting to Internet resources and distribution method, and controller | |
CN105787771A (en) | Method and system for improving stability of data interaction in network invoice system | |
CN110391995A (en) | A kind of RPL network load balancing method and device |
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 |