CN104579963A - Method and device for optimizing routes of nodes - Google Patents
Method and device for optimizing routes of nodes Download PDFInfo
- Publication number
- CN104579963A CN104579963A CN201510044898.7A CN201510044898A CN104579963A CN 104579963 A CN104579963 A CN 104579963A CN 201510044898 A CN201510044898 A CN 201510044898A CN 104579963 A CN104579963 A CN 104579963A
- Authority
- CN
- China
- Prior art keywords
- node
- route
- distance value
- directly connected
- weights
- 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
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a method and a device for optimizing routes of nodes. The method includes: S1, setting an initial simulation weight topology; S2, selecting one node from the initial simulation weight topology to serve as an initial node, and taking other nodes as target nodes, determining an optimal route from the initial node to each target node, and determining a distance value of each optimal route; S3, updating an initial transmission path pressure weight in the initial simulation weight topology and a relay forward delay weight of the initial node; S4, returning to execute the S2-S4 according to the updated simulation weight topology until optimal routes of all nodes are calculated. By adoption of the scheme, optimization in transmission among nodes of a whole system is realized, and operation performances of the system are greatly improved.
Description
Technical field
The present invention relates to field of computer technology, particularly the optimization method of route and device between a kind of node.
Background technology
Along with the development of computer technology, every field, such as, the development of new material, wind tunnel test emulation, oil exploration and exploitation etc., all be unable to do without high-end computer.Wherein, the systematic function of high-end computer is the main competition spot of each model high-end computer.
At present, extendible high-end computer system, is generally made up of multiple node.Wherein, different number of nodes can form the computer system of different scales.Conventional scale can be 16 tunnels, 32 roads and 64 tunnels.Because the internet topology between node is often very complicated, between node, routing Design unreasonable may cause the transmission line of internodal message to be blocked or the problem such as transfer delay, greatly reduces the performance of whole high-end computer system.
Summary of the invention
In view of this, the invention provides optimization method and the device of route between a kind of node, to realize the optimization of each internodal route.
The invention provides the optimization method of route between a kind of node, for every two internodal circuits arrange corresponding initial transmission route pressure weights, the start node relay forwarding corresponding for each Node configuration postpones weights; For every two internodal circuits arrange transmission route pressure coefficient and node relay forwarding retardation coefficient, comprising:
S1: the start node relay forwarding according to the annexation of each node and initial transmission route pressure weights corresponding to every two internodal circuits, each Node configuration postpones weights, sets up primary simulation weights topology;
S2: will not be selected as in the node of start node in described primary simulation weights topology, select a node as start node, using other nodes as destination node, determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route;
S3: divide the optimum route being clipped to each destination node according to the start node determined, according to the distance value of each the optimum route determined, and according to the transmission route pressure coefficient preset and node relay forwarding retardation coefficient, upgrade the initial transmission route pressure weights in described primary simulation weights topology and start node relay forwarding delay weights;
S4: topological according to the simulation weights after upgrading, returns and performs S2-S4, until calculate the optimum route of all nodes.
Preferably, describedly determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route, comprising:
S31: determine the destination node be directly connected with start node, calculates the current route of start node to the destination node be directly connected with start node, and calculates the distance value of each current route; Calculate the distance value of each current route and, and the number of destination node that statistics is not directly connected with start node;
S32: according to the distance value of each the current route calculated, not by the destination node selected in as each destination node determining routing node corresponding to the current route of lowest distance value as determining routing node; Obtain and determine the destination node that routing node is directly connected, calculate start node divide the destination node that is clipped to and is directly connected with described start node and with the renewal route determining the destination node that routing node is directly connected, and calculate the distance value that each upgrades route respectively; Calculate each upgrade the distance value of route and, and statistics not directly to be connected with start node and with the number determining the destination node that routing node is not directly connected;
S33: the number of the destination node that the described and start node of comparative statistics is not directly connected, not directly to be connected with start node with described and with the number determining the destination node that routing node is not directly connected;
If the number of the described destination node be not directly connected with start node be less than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, retain current route;
If the number of the described destination node be not directly connected with start node be greater than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, renewal route is replaced current route;
If the number of the described destination node be not directly connected with start node equal described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, the distance value of each the current route described relatively calculated and, with described each upgrades the distance value of route with; If the distance value of each current route described and be less than described each upgrade the distance value of route and, retain current route; If the distance value of each current route described and be greater than described each upgrade the distance value of route and, renewal route is replaced current route;
S34: according to the current route obtained in S33, perform S32-S34, until destination node in each node except start node is all by as when determining routing node, divide as described start node the optimum route being clipped to each destination node using the current route now obtained, and using the distance value of each current route in the current route now obtained as the distance value of each optimum route.
Preferably, the distance value of described calculating route, comprising: when calculating the distance value of route, utilize following formulae discovery:
S＝P
1+L
1*M*P
1+K
1*N+P
2+L
2*M*P
2+K
2*N+……+P
t+L
t*M*P
t
Wherein, S is the distance value of calculative route, Pt is the transmission route pressure weights through t article of circuit, Lt is the transmission pressure on t article of circuit, M is transmission route pressure coefficient, Kt is the relay task pressure of t via node, and N represents the node relay forwarding retardation coefficient of via node.
Preferably, described is that every two internodal circuits arrange corresponding initial transmission route pressure weights, is that the start node relay forwarding that each Node configuration is corresponding postpones weights, comprises:
Arrange corresponding initial transmission route pressure weights according to the transmission performance of every two internodal routes, wherein, two internodal transmission performances are larger, arrange corresponding initial transmission route pressure weights larger; Arrange corresponding start node relay forwarding according to the forwarding performance of each node and postpone weights, wherein, the forwarding performance of node is larger, arranges corresponding start node relay forwarding delay weights larger.
Preferably, comprise further:
S5: in the optimum route of all nodes calculated, according to the distance value of the optimum route of each start node and, using lowest distance value with corresponding start node as host node.
The invention provides the optimization device of route between a kind of node, comprising:
Memory cell, arrange corresponding initial transmission route pressure weights for saving as every two internodal circuits, the start node relay forwarding corresponding for each Node configuration postpones weights; For every two internodal circuits arrange transmission route pressure coefficient and node relay forwarding retardation coefficient;
Setting up unit, for postponing weights according to the start node relay forwarding of the annexation of each node and initial transmission route pressure weights corresponding to every two internodal circuits, each Node configuration, setting up primary simulation weights topology;
Determining unit, for not being selected as in the node of start node in described primary simulation weights topology, select a node as start node, using other nodes as destination node, determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route;
Updating block, for dividing the optimum route being clipped to each destination node according to the start node determined, according to the distance value of each the optimum route determined, and according to the transmission route pressure coefficient preset and node relay forwarding retardation coefficient, upgrade the initial transmission route pressure weights in described primary simulation weights topology and start node relay forwarding delay weights;
Computing unit, for topological according to the simulation weights after renewal, and continues to utilize described determining unit, described updating block and computing unit to perform, until calculate the optimum route of all nodes.
Preferably, described determining unit, for determining the destination node be directly connected with start node, calculating the current route of start node to the destination node be directly connected with start node, and calculating the distance value of each current route; Calculate the distance value of each current route and, and the number of destination node that statistics is not directly connected with start node; According to the distance value of each the current route calculated, not by the destination node selected in as each destination node determining routing node corresponding to the current route of lowest distance value as determining routing node; Obtain and determine the destination node that routing node is directly connected, calculate start node divide the destination node that is clipped to and is directly connected with described start node and with the renewal route determining the destination node that routing node is directly connected, and calculate the distance value that each upgrades route respectively; Calculate each upgrade the distance value of route and, and statistics not directly to be connected with start node and with the number determining the destination node that routing node is not directly connected; The number of the destination node that the described and start node of comparative statistics is not directly connected, not directly to be connected with start node with described and with the number determining the destination node that routing node is not directly connected; If the number of the described destination node be not directly connected with start node be less than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, retain current route; If the number of the described destination node be not directly connected with start node be greater than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, renewal route is replaced current route; If the number of the described destination node be not directly connected with start node equal described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, the distance value of each the current route described relatively calculated and, with described each upgrades the distance value of route with; If the distance value of each current route described and be less than described each upgrade the distance value of route and, retain current route; If the distance value of each current route described and be greater than described each upgrade the distance value of route and, renewal route is replaced current route; According to the current route obtained, the distance value continuing each the current route calculated from described basis performs, until destination node in each node except start node is all by as when determining routing node, divide as described start node the optimum route being clipped to each destination node using the current route now obtained, and using the distance value of each current route in the current route now obtained as the distance value of each optimum route.
Preferably, described computing unit, for when calculating the distance value of route, utilizes following formulae discovery:
S＝P
1+L
1*M*P
1+K
1*N+P
2+L
2*M*P
2+K
2*N+……+P
t+L
t*M*P
t
Wherein, S is the distance value of calculative route, Pt is the transmission route pressure weights through t article of circuit, Lt is the transmission pressure on t article of circuit, M is transmission route pressure coefficient, Kt is the relay task pressure of t via node, and N represents the node relay forwarding retardation coefficient of via node.
Preferably, described memory cell, for arranging corresponding initial transmission route pressure weights according to the transmission performance of every two internodal routes, wherein, two internodal transmission performances are larger, arrange corresponding initial transmission route pressure weights larger; Arrange corresponding start node relay forwarding according to the forwarding performance of each node and postpone weights, wherein, the forwarding performance of node is larger, arranges corresponding start node relay forwarding delay weights larger.
Preferably, comprise further:
Host node selected cell, in the optimum route of all nodes calculated, according to the distance value of the optimum route of each start node and, using lowest distance value with corresponding start node as host node.
Embodiments provide optimization method and the device of route between a kind of node, by setting up simulation weights topology, to selecting a node as start node in the node not being selected as start node in each node, and route balance algorithm is performed to this start node, to realize the routing infrastructure of transmission route isostasy and node relay forwarding delay equalization, thus achieve the optimization of whole system inter-node transmission, greatly improve the service behaviour of system.
Accompanying drawing explanation
Fig. 1 is the method flow diagram that the embodiment of the present invention provides;
Fig. 2 is the method flow diagram that another embodiment of the present invention provides;
Fig. 3 is the node topology schematic diagram that the embodiment of the present invention provides;
Fig. 4 is the simulation weights topology schematic diagram that the embodiment of the present invention provides;
Fig. 5 is the schematic diagram of the execution proportional routing algorithm that the embodiment of the present invention provides;
Fig. 6 is the simulation weights topology schematic diagram after the renewal that provides of the embodiment of the present invention;
Fig. 7 is the hardware structure figure of the device place equipment that the embodiment of the present invention provides;
Fig. 8 is the apparatus structure schematic diagram that the embodiment of the present invention provides;
Fig. 9 is the apparatus structure schematic diagram that another embodiment of the present invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described.Obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As shown in Figure 1, embodiments provide the optimization method of route between a kind of node, for every two internodal circuits arrange corresponding initial transmission route pressure weights, the start node relay forwarding corresponding for each Node configuration postpones weights; For every two internodal circuits arrange transmission route pressure coefficient and node relay forwarding retardation coefficient, the method can comprise:
Step 101: the start node relay forwarding according to the annexation of each node and initial transmission route pressure weights corresponding to every two internodal circuits, each Node configuration postpones weights, sets up primary simulation weights topology.
Step 102: will not be selected as in the node of start node in described primary simulation weights topology, select a node as start node, using other nodes as destination node, determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route.
Step 103: divide the optimum route being clipped to each destination node according to the start node determined, according to the distance value of each the optimum route determined, and according to the transmission route pressure coefficient preset and node relay forwarding retardation coefficient, upgrade the initial transmission route pressure weights in described primary simulation weights topology and start node relay forwarding delay weights.
Step 104: topological according to the described simulation weights after upgrading, returns and performs S2-S4, until calculate the optimum route of all nodes.
According to such scheme, by setting up simulation weights topology, to selecting a node as start node in the node not being selected as start node in each node, and route balance algorithm is performed to this start node, to realize the routing infrastructure of transmission route isostasy and node relay forwarding delay equalization, thus achieve the optimization of whole system inter-node transmission, greatly improve the service behaviour of system.
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with drawings and the specific embodiments, the present invention is described in further detail.
As shown in Figure 2, embodiments provide the optimization method of route between a kind of node, the method can comprise the following steps:
Step 201: for every two internodal circuits arrange corresponding initial transmission route pressure weights, the start node relay forwarding corresponding for each Node configuration postpones weights; For every two internodal circuits arrange transmission route pressure coefficient and node relay forwarding retardation coefficient.
As shown in Figure 3, for the annexation of each node in system, wherein, node 1, node 2, node 3, node 4 is in a cabinet, (1-2) (1-3) and node 1 is connected with node 3 with node 2 respectively, node 2 and node 3 are all connected with node 4 (2-4) (3-4); Node 5 and node 6 are connected (5-6) in another cabinet.The intermediate node 2 of two cabinets is connected with node 5 (2-5), and node 4 is connected (4-6) with node 6.Wherein, transmission route distance between cabinet is greater than cabinet intraconnections distance, and therefore, the transmission performance of the transmission route between cabinet is poorer than the transmission performance of cabinet intraconnections, wherein, set (4-6) and use transmission performance ratio (2-5) preferably line.
Therefore, corresponding initial transmission route pressure weights can be set according to the transmission performance of every two internodal routes, corresponding start node relay forwarding be set according to the forwarding performance of each node and postpone weights.The transmission route that cabling between node is shorter, transmission performance is better, weights are less; The transmission route that cabling is longer, transmission performance is poorer, weights are larger.Suppose (1-2), (1-3), (2-4), (3-4) and (5-6) initial transmission route pressure weights be 2; (2-5) initial transmission route pressure weights are 6; (4-6) initial transmission route pressure weights are 4.The start node relay forwarding arranging each via node postpones weights and is 1, and wherein, via node refers to for carrying out the node forwarded.
Step 202: the start node relay forwarding according to the annexation of each node in system and initial transmission route pressure weights corresponding to every two internodal circuits, each Node configuration postpones weights, sets up primary simulation weights topology.
As shown in Figure 4, according to each internodal connection in Fig. 3, set up primary simulation weights topology.Wherein, in primary simulation weights topology, each internodal topological relation does not change, and is only on being added by the initial transmission route pressure weights of every two internodal circuits.
Step 203: will not be selected as in the node of start node in primary simulation weights topology, select a node as start node, using other nodes as destination node, determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route.
In the present embodiment, respectively using each node of primary simulation weights topology as start node, route balance algorithm is performed to each start node.Wherein, as shown in Figure 5, route balance algorithm comprises:
Step 501: determine the destination node be directly connected with start node, calculates the current route of start node to the destination node be directly connected with start node, and calculates the distance value of each current route; Calculate the distance value of each current route and, and the number of destination node that statistics is not directly connected with start node.
Step 502: according to the distance value of each the current route calculated, not by the destination node selected in as each destination node determining routing node corresponding to the current route of lowest distance value as determining routing node; Obtain and determine the destination node that routing node is directly connected, calculate start node divide the destination node that is clipped to and is directly connected with start node and with the renewal route determining the destination node that routing node is directly connected, and calculate the distance value that each upgrades route respectively; Calculate each upgrade the distance value of route and, and statistics not directly to be connected with start node and with the number determining the destination node that routing node is not directly connected.
Step 503: the number of the destination node be not directly connected with start node of comparative statistics, be not directly connected with start node and with the number determining the destination node that routing node is not directly connected;
If the number of the destination node be not directly connected with start node be less than directly not to be connected with start node and with the number determining the destination node that routing node is not directly connected, retain current route;
If the number of the destination node be not directly connected with start node be greater than directly not to be connected with start node and with the number determining the destination node that routing node is not directly connected, renewal route is replaced current route;
If the number of the destination node be not directly connected with start node equal directly not to be connected with start node and with the number determining the destination node that routing node is not directly connected, the distance value of each the current route relatively calculated and, with each upgrades the distance value of route with; If the distance value of each current route and be less than each upgrade route distance value and, retain current route; If the distance value of each current route and be greater than each upgrade route distance value and, renewal route is replaced current route.
Step 504: according to the current route obtained in step 503, perform step 502-step 504, until destination node in each node except start node is all by as when determining routing node, divide as start node the optimum route being clipped to each destination node using the current route now obtained, and using the distance value of each current route in the current route now obtained as the distance value of each optimum route.
In order to make process start node being performed to route balance algorithm more clear, below using node 1 as start node, node 2, node 3, node 4, node 5 and node 6 are example as destination node, perform route balance algorithm be described node 1.
According to step 501, determine current route.
First, determine and the destination node that node 1 is directly connected, i.e. node 2 as shown in Figure 5 and node 3.
Next, the current route that difference computing node 1 arrives node 2, node 1 arrives node 3, and the distance value that computing node 1 arrives node 2 respectively, node 1 arrives node 3.
In the present embodiment, computing node 1 is respectively to node 2, node 1 to the current route of node 3: 1 → 2,1 → 3.
In the present embodiment, due to the transmission route pressure weights between node are different and node relay forwarding to postpone weights different, during distance value therefore between computing node, need to add transmission route pressure weights and node relay forwarding postpones weights.Wherein, suppose that transmission route pressure coefficient is M=0.5, node relay forwarding retardation coefficient is N=5.For one deck transmission many on internodal transmission route, its transmission route pressure weights increase the M of former transmission route pressure weights doubly; And for each via node (node namely for forwarding) when often increasing a relay task, the node relay forwarding of this via node postpones weights increases N.Such as, be: X → Y → Z that wherein, the transmission route pressure weights of X → Y are that A, X → Y corresponds to two-layer transmission, and the transmission route pressure weights of Y → Z are B, and Y → Z corresponds to one deck transmission, and Y only has a relay forwarding task for a transmission route.So, the distance value of X → Y is: S (X-Y)=A+2MA; The distance value of X → Y → Z is: S (X-Y-Z)=A+2MA+B+MB+N.
In the present embodiment, following formula (1) can be used to calculate when calculating the distance value of route:
S＝P
1+L
1*M*P
1+K
1*N+P
2+L
2*M*P
2+K
2*N+……+P
t+L
t*M*P
t(1)
Wherein, S is the distance value of calculative route, Pt is the transmission route pressure weights through t article of circuit, Lt is the transmission pressure on t article of circuit, M is transmission route pressure coefficient, Kt is the relay task pressure of t via node, and N represents the node relay forwarding retardation coefficient of via node.
Therefore, computing node 1 comprises to node 2, node 1 to the distance value of node 3 respectively: S (1-2)=2+M*2=3; S (1-3)=2+M*2=3.
Again, computing node 1 to node 2 distance value and node 1 to node 3 distance value with, i.e. S (1-2)+S (1-3)=6.And add up the number of the destination node be not directly connected with node 1: node 4, node 5 and node 6 totally 3.
In the present embodiment, setting node 1 is NA to the route of the destination node be not directly connected with node 1, and distance value is 0xff.
As shown in table 1, using the statistical form that obtains according to step 501 as current route:
Table 1:
According to step 502, continue to determine to upgrade route.
First, according to the distance value of each the current route calculated, not by the destination node selected in as each destination node determining routing node corresponding to the current route of lowest distance value as determining routing node.Wherein, using node 2 as determining routing node.
Secondly, obtain and determine the destination node that routing node is directly connected, namely with the node 4 be connected between node 2 and node 5.
Again, computing node 1 is respectively to node 4, node 1 to the renewal route of node 5 to node 2, node 1 to node 3, node 1: 1 → 2,1 → 3,1 → 2 → 4,1 → 2 → 5, and the distance value calculating each renewal route is respectively respectively: S (1-2)=2+3*M*2=5; S (1-3)=2+M*2=3; S (1-2-4)=S (1-2)+2+M*2+N*2=18; S (1-2-5)=S (1-2)+6+M*6+N*2=24.
Finally, calculate each upgrade route distance value and, i.e. S (1-2)+S (1-3)+S (1-2-4)+S (1-2-5)=50, and statistics is not directly connected and the number of the destination node be not directly connected with node 2 with node 1, i.e. node 6 totally 1.
As shown in table 2, for the statistical form obtained according to step 502 is as renewal route:
Table 2
According to step 503, determine to retain the current route obtained.
According to table 1 and table 2 known, the number 3 of the destination node be not directly connected with node 1 in comparison sheet 1, be greater than in table 2 be not directly connected with node 1 and with the number 1 determining the destination node that routing node is not directly connected, therefore, the renewal route of reservation table 2 correspondence, by the renewal route of table 2 correspondence as current route.
According to step 504, determine that start node divides the route being clipped to each destination node, and determine the distance value of each route.
First, according to the current route of table 2 correspondence, using node 3 as determining routing node.As table 3
Shown in, using according to node 3 as determine the statistical form of routing node as renewal route:
Table 3:
According to table 2 and table 3 known, directly be not connected with node 1 in comparison sheet 2 and with the number 1 determining the destination node that routing node is not directly connected, equal directly not to be connected with node 1 in table 3 and with the number 1 determining the destination node that routing node is not directly connected, therefore, need more known further, in table 2 each route distance value with 50, be greater than the distance value of each route in table 3 with 38, therefore, the renewal route of reservation table 3 correspondence, by the renewal route of table 3 correspondence as current route.
Secondly, according to the current route of table 3 correspondence, using node 4 as determining routing node.As shown in table 4, using according to node 4 as determine the statistical form of routing node as renewal route:
Table 4:
According to table 3 and table 4 known, directly be not connected with node 1 in comparison sheet 3 and with the number 1 determining the destination node that routing node is not directly connected, be greater than in table 4 be not directly connected with node 1 and with the number 0 determining the destination node that routing node is not directly connected, therefore, the renewal route of reservation table 4 correspondence, by the renewal route of table 4 correspondence as current route.
Again, according to the current route of table 4 correspondence, using node 5 as determining routing node.As shown in table 5, using according to node 5 as determine the statistical form of routing node as renewal route:
Table 5:
According to table 4 and table 5 known, directly be not connected with node 1 in comparison sheet 4 and with the number 0 determining the destination node that routing node is not directly connected, equal directly not to be connected with node 1 in table 5 and with the number 0 determining the destination node that routing node is not directly connected, therefore, need more known further, in table 4 each route distance value with 76, be less than the distance value of each route in table 5 with 83, therefore, the current route of reservation table 4 correspondence.
Again, according to the current route of table 4 correspondence, using node 6 as determining routing node.As shown in table 6, using according to node 6 as determine the statistical form of routing node as renewal route:
Table 6:
According to table 4 and table 6 known, directly be not connected with node 1 in table 4 and with determine the number of the destination node that routing node is not directly connected directly not to be connected with node 1 with table 6 and with the number determining the destination node that routing node is not directly connected, and in table 4 each route distance value and with the distance value of each route in table 6 and all equal, and because all destination nodes in table 6 are all by as determining routing node, therefore, using table 6 as final route, wherein, the route that node in table 61 point is clipped to each destination node divides the route being clipped to each destination node as start node, and the distance value of each route in table 6 is as the distance value of each route determined.
Step 204: divide the optimum route being clipped to each destination node according to the start node determined, according to the distance value of each the optimum route determined, and according to the transmission route pressure coefficient preset and node relay forwarding retardation coefficient, upgrade the initial transmission route pressure weights in primary simulation weights topology and start node relay forwarding delay weights.
As shown in Figure 6, for the simulation weights after upgrading are topological, wherein, transmission route pressure weights between node 1 to node 2 are 4, transmission route pressure weights between node 1 to node 3 are 5, node 2 is 2 to the transmission route pressure weights of node 4, node 3 is 4 to the transmission route pressure weights of node 4, node 2 is 9 to the transmission route pressure weights of node 5, node 4 is 6 to the transmission route pressure weights of node 6, node 5 is 2 to the transmission route pressure weights of node 6, it is 5 that the node relay forwarding of node 2 postpones weights, it is 10 that the node relay forwarding of node 3 postpones weights, it is 5 that the node relay forwarding of node 4 postpones weights.
Step 205: topological according to the simulation weights after upgrading, performs step 203 to step 205, until calculate the optimum route of all nodes.
In the present embodiment, need using node 2 as start node, using node 1, node 3, node 4, node 5, node 6 as destination node, proportional routing algorithm is performed to node 2; Using node 3 as start node, using node 1, node 2, node 4, node 5, node 6 as destination node, proportional routing algorithm is performed to node 3; Need using node 4 as start node, using node 1, node 2, node 3, node 5, node 6 as destination node, proportional routing algorithm is performed to node 4; Need using node 5 as start node, using node 1, node 2, node 3, node 4, node 6 as destination node, proportional routing algorithm is performed to node 5; Need using node 6 as start node, using node 1, node 2, node 3, node 4, node 5 as destination node, proportional routing algorithm is performed to node 6.Now, obtain each start node and divide the route being clipped to each destination node, complete the routing optimality to each start node.
Step 206: in the optimum route of all nodes calculated, according to the distance value of the optimum route of each start node and, using lowest distance value with corresponding start node as host node.
In the present embodiment, during to node 1, node 2, node 3, node 4, node 5 and node 6 respectively as start node, the distance value of the corresponding destination node that can access and sort, the distance value of the destination node that can access with the start node corresponding to minimum value as host node.
According to such scheme, by setting up simulation weights topology, to selecting a node as start node in the node not being selected as start node in each node, and route balance algorithm is performed to this start node, to realize the routing infrastructure of transmission route isostasy and node relay forwarding delay equalization, thus achieve the optimization of whole system inter-node transmission, greatly improve the service behaviour of system.
As shown in Figure 7, Figure 8, the optimization device of route between a kind of node is embodiments provided.Device embodiment can pass through software simulating, also can be realized by the mode of hardware or software and hardware combining.Say from hardware view; as shown in Figure 7; for a kind of hardware structure diagram of the optimization device place equipment of route between embodiment of the present invention node; except the processor shown in Fig. 7, internal memory, network interface and nonvolatile memory; in embodiment, the equipment at device place can also comprise other hardware usually, as the forwarding chip etc. of responsible process message.For software simulating, as shown in Figure 8, as the device on a logical meaning, be by the CPU of its place equipment, computer program instructions corresponding in nonvolatile memory is read operation in internal memory to be formed.Between the node that the present embodiment provides, the optimization device 80 of route comprises:
Memory cell 801, arrange corresponding initial transmission route pressure weights for saving as every two internodal circuits, the start node relay forwarding corresponding for each Node configuration postpones weights; For every two internodal circuits arrange transmission route pressure coefficient and node relay forwarding retardation coefficient;
Setting up unit 802, for postponing weights according to the start node relay forwarding of the annexation of each node and initial transmission route pressure weights corresponding to every two internodal circuits, each Node configuration, setting up primary simulation weights topology;
Determining unit 803, for not being selected as in the node of start node in described primary simulation weights topology, select a node as start node, using other nodes as destination node, determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route;
Updating block 804, for dividing the optimum route being clipped to each destination node according to the start node determined, according to the distance value of each the optimum route determined, and according to the transmission route pressure coefficient preset and node relay forwarding retardation coefficient, upgrade the initial transmission route pressure weights in described primary simulation weights topology and start node relay forwarding delay weights;
Computing unit 805, for topological according to the simulation weights after renewal, and continues to utilize described determining unit, described updating block and computing unit to perform, until calculate the optimum route of all nodes.
Further, described determining unit 803, for determining the destination node be directly connected with start node, calculating the current route of start node to the destination node be directly connected with start node, and calculating the distance value of each current route; Calculate the distance value of each current route and, and the number of destination node that statistics is not directly connected with start node; According to the distance value of each the current route calculated, not by the destination node selected in as each destination node determining routing node corresponding to the current route of lowest distance value as determining routing node; Obtain and determine the destination node that routing node is directly connected, calculate start node divide the destination node that is clipped to and is directly connected with described start node and with the renewal route determining the destination node that routing node is directly connected, and calculate the distance value that each upgrades route respectively; Calculate each upgrade the distance value of route and, and statistics not directly to be connected with start node and with the number determining the destination node that routing node is not directly connected; The number of the destination node that the described and start node of comparative statistics is not directly connected, not directly to be connected with start node with described and with the number determining the destination node that routing node is not directly connected; If the number of the described destination node be not directly connected with start node be less than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, retain current route; If the number of the described destination node be not directly connected with start node be greater than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, renewal route is replaced current route; If the number of the described destination node be not directly connected with start node equal described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, the distance value of each the current route described relatively calculated and, with described each upgrades the distance value of route with; If the distance value of each current route described and be less than described each upgrade the distance value of route and, retain current route; If the distance value of each current route described and be greater than described each upgrade the distance value of route and, renewal route is replaced current route; According to the current route obtained, the distance value continuing each the current route calculated from described basis performs, until destination node in each node except start node is all by as when determining routing node, divide as described start node the optimum route being clipped to each destination node using the current route now obtained, and using the distance value of each current route in the current route now obtained as the distance value of each optimum route.
Further, described computing unit 805, for when calculating the distance value of route, utilizes following formulae discovery:
S＝P
1+L
1*M*P
1+K
1*N+P
2+L
2*M*P
2+K
2*N+……+P
t+L
t*M*P
t
Wherein, S is the distance value of calculative route, Pt is the transmission route pressure weights through t article of circuit, Lt is the transmission pressure on t article of circuit, M is transmission route pressure coefficient, Kt is the relay task pressure of t via node, and N represents the node relay forwarding retardation coefficient of via node.
Further, described memory cell 801, for arranging corresponding initial transmission route pressure weights according to the transmission performance of every two internodal routes, wherein, two internodal transmission performances are larger, arrange corresponding initial transmission route pressure weights larger; Arrange corresponding start node relay forwarding according to the forwarding performance of each node and postpone weights, wherein, the forwarding performance of node is larger, arranges corresponding start node relay forwarding delay weights larger.
In an embodiment of the invention, as shown in Figure 9, comprise further:
Host node selected cell 901, in the optimum route of all nodes calculated, according to the distance value of the optimum route of each start node and, using lowest distance value with corresponding start node as host node.
The content such as information interaction, implementation between each unit in the said equipment, due to the inventive method embodiment based on same design, particular content can see in the inventive method embodiment describe, repeat no more herein.
It should be noted that, in this article, the relational terms of such as first and second and so on is only used for an entity or operation to separate with another entity or operating space, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element " being comprised " limited by statement, and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical factor.
One of ordinary skill in the art will appreciate that: all or part of step realizing said method embodiment can have been come by the hardware that program command is relevant, aforesaid program can be stored in the storage medium of embodied on computer readable, this program, when performing, performs the step comprising said method embodiment; And aforesaid storage medium comprises: ROM, RAM, magnetic disc or CD etc. various can be program code stored medium in.
Finally it should be noted that: the foregoing is only preferred embodiment of the present invention, only for illustration of technical scheme of the present invention, be not intended to limit protection scope of the present invention.All any amendments done within the spirit and principles in the present invention, equivalent replacement, improvement etc., be all included in protection scope of the present invention.
Claims (10)
1. the optimization method of route between node, is characterized in that, for every two internodal circuits arrange corresponding initial transmission route pressure weights, is that the start node relay forwarding that each Node configuration is corresponding postpones weights; For every two internodal circuits arrange transmission route pressure coefficient and node relay forwarding retardation coefficient, comprising:
S1: the start node relay forwarding according to the annexation of each node and initial transmission route pressure weights corresponding to every two internodal circuits, each Node configuration postpones weights, sets up primary simulation weights topology;
S2: will not be selected as in the node of start node in described primary simulation weights topology, select a node as start node, using other nodes as destination node, determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route;
S3: divide the optimum route being clipped to each destination node according to the start node determined, according to the distance value of each the optimum route determined, and according to the transmission route pressure coefficient preset and node relay forwarding retardation coefficient, upgrade the initial transmission route pressure weights in described primary simulation weights topology and start node relay forwarding delay weights;
S4: topological according to the simulation weights after upgrading, returns and performs S2-S4, until calculate the optimum route of all nodes.
2. method according to claim 1, is characterized in that, describedly determines that start node divides the optimum route being clipped to each destination node, and determines the distance value of each optimum route, comprising:
S31: determine the destination node be directly connected with start node, calculates the current route of start node to the destination node be directly connected with start node, and calculates the distance value of each current route; Calculate the distance value of each current route and, and the number of destination node that statistics is not directly connected with start node;
S32: according to the distance value of each the current route calculated, not by the destination node selected in as each destination node determining routing node corresponding to the current route of lowest distance value as determining routing node; Obtain and determine the destination node that routing node is directly connected, calculate start node divide the destination node that is clipped to and is directly connected with described start node and with the renewal route determining the destination node that routing node is directly connected, and calculate the distance value that each upgrades route respectively; Calculate each upgrade the distance value of route and, and statistics not directly to be connected with start node and with the number determining the destination node that routing node is not directly connected;
S33: the number of the destination node that the described and start node of comparative statistics is not directly connected, not directly to be connected with start node with described and with the number determining the destination node that routing node is not directly connected;
If the number of the described destination node be not directly connected with start node be less than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, retain current route;
If the number of the described destination node be not directly connected with start node be greater than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, renewal route is replaced current route;
If the number of the described destination node be not directly connected with start node equal described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, the distance value of each the current route described relatively calculated and, with described each upgrades the distance value of route with; If the distance value of each current route described and be less than described each upgrade the distance value of route and, retain current route; If the distance value of each current route described and be greater than described each upgrade the distance value of route and, renewal route is replaced current route;
S34: according to the current route obtained in S33, perform S32-S34, until destination node in each node except start node is all by as when determining routing node, divide as described start node the optimum route being clipped to each destination node using the current route now obtained, and using the distance value of each current route in the current route now obtained as the distance value of each optimum route.
3. method according to claim 2, is characterized in that, the distance value of described calculating route, comprising: when calculating the distance value of route, utilize following formulae discovery:
S＝P
1+L
1*M*P
1+K
1*N+P
2+L
2*M*P
2+K
2*N+……+P
t+L
t*M*P
t
Wherein, S is the distance value of calculative route, Pt is the transmission route pressure weights through t article of circuit, Lt is the transmission pressure on t article of circuit, M is transmission route pressure coefficient, Kt is the relay task pressure of t via node, and N represents the node relay forwarding retardation coefficient of via node.
4. method according to claim 1, is characterized in that, described is that every two internodal circuits arrange corresponding initial transmission route pressure weights, is that the start node relay forwarding that each Node configuration is corresponding postpones weights, comprises:
Arrange corresponding initial transmission route pressure weights according to the transmission performance of every two internodal routes, wherein, two internodal transmission performances are larger, arrange corresponding initial transmission route pressure weights larger; Arrange corresponding start node relay forwarding according to the forwarding performance of each node and postpone weights, wherein, the forwarding performance of node is larger, arranges corresponding start node relay forwarding delay weights larger.
5., according to described method arbitrary in Claims 1-4, it is characterized in that, comprise further:
S5: in the optimum route of all nodes calculated, according to the distance value of the optimum route of each start node and, using lowest distance value with corresponding start node as host node.
6. the optimization device of route between node, is characterized in that, comprising:
Memory cell, arrange corresponding initial transmission route pressure weights for saving as every two internodal circuits, the start node relay forwarding corresponding for each Node configuration postpones weights; For every two internodal circuits arrange transmission route pressure coefficient and node relay forwarding retardation coefficient;
Setting up unit, for postponing weights according to the start node relay forwarding of the annexation of each node and initial transmission route pressure weights corresponding to every two internodal circuits, each Node configuration, setting up primary simulation weights topology;
Determining unit, for not being selected as in the node of start node in described primary simulation weights topology, select a node as start node, using other nodes as destination node, determine that start node divides the optimum route being clipped to each destination node, and determine the distance value of each optimum route;
Updating block, for dividing the optimum route being clipped to each destination node according to the start node determined, according to the distance value of each the optimum route determined, and according to the transmission route pressure coefficient preset and node relay forwarding retardation coefficient, upgrade the initial transmission route pressure weights in described primary simulation weights topology and start node relay forwarding delay weights;
Computing unit, for topological according to the simulation weights after renewal, and continues to utilize described determining unit, described updating block and computing unit to perform, until calculate the optimum route of all nodes.
7. device according to claim 6, it is characterized in that, described determining unit, for determining the destination node be directly connected with start node, calculate the current route of start node to the destination node be directly connected with start node, and calculate the distance value of each current route; Calculate the distance value of each current route and, and the number of destination node that statistics is not directly connected with start node; According to the distance value of each the current route calculated, not by the destination node selected in as each destination node determining routing node corresponding to the current route of lowest distance value as determining routing node; Obtain and determine the destination node that routing node is directly connected, calculate start node divide the destination node that is clipped to and is directly connected with described start node and with the renewal route determining the destination node that routing node is directly connected, and calculate the distance value that each upgrades route respectively; Calculate each upgrade the distance value of route and, and statistics not directly to be connected with start node and with the number determining the destination node that routing node is not directly connected; The number of the destination node that the described and start node of comparative statistics is not directly connected, not directly to be connected with start node with described and with the number determining the destination node that routing node is not directly connected; If the number of the described destination node be not directly connected with start node be less than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, retain current route; If the number of the described destination node be not directly connected with start node be greater than described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, renewal route is replaced current route; If the number of the described destination node be not directly connected with start node equal described be not directly connected with start node and with the number determining the destination node that routing node is not directly connected, the distance value of each the current route described relatively calculated and, with described each upgrades the distance value of route with; If the distance value of each current route described and be less than described each upgrade the distance value of route and, retain current route; If the distance value of each current route described and be greater than described each upgrade the distance value of route and, renewal route is replaced current route; According to the current route obtained, the distance value continuing each the current route calculated from described basis performs, until destination node in each node except start node is all by as when determining routing node, divide as described start node the optimum route being clipped to each destination node using the current route now obtained, and using the distance value of each current route in the current route now obtained as the distance value of each optimum route.
8. device according to claim 7, is characterized in that, described computing unit, for when calculating the distance value of route, utilizes following formulae discovery:
S＝P
1+L
1*M*P
1+K
1*N+P
2+L
2*M*P
2+K
2*N+……+P
t+L
t*M*P
t
Wherein, S is the distance value of calculative route, Pt is the transmission route pressure weights through t article of circuit, Lt is the transmission pressure on t article of circuit, M is transmission route pressure coefficient, Kt is the relay task pressure of t via node, and N represents the node relay forwarding retardation coefficient of via node.
9. device according to claim 6, it is characterized in that, described memory cell, for arranging corresponding initial transmission route pressure weights according to the transmission performance of every two internodal routes, wherein, two internodal transmission performances are larger, arrange corresponding initial transmission route pressure weights larger; Arrange corresponding start node relay forwarding according to the forwarding performance of each node and postpone weights, wherein, the forwarding performance of node is larger, arranges corresponding start node relay forwarding delay weights larger.
10., according to described device arbitrary in claim 6 to 9, it is characterized in that, comprise further:
Host node selected cell, in the optimum route of all nodes calculated, according to the distance value of the optimum route of each start node and, using lowest distance value with corresponding start node as host node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510044898.7A CN104579963B (en) | 2015-01-28 | 2015-01-28 | A kind of optimization method and device being route between node |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510044898.7A CN104579963B (en) | 2015-01-28 | 2015-01-28 | A kind of optimization method and device being route between node |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104579963A true CN104579963A (en) | 2015-04-29 |
| CN104579963B CN104579963B (en) | 2017-06-30 |
Family
ID=53095193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510044898.7A Active CN104579963B (en) | 2015-01-28 | 2015-01-28 | A kind of optimization method and device being route between node |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104579963B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105827453A (en) * | 2016-04-25 | 2016-08-03 | 浪潮电子信息产业股份有限公司 | Method for setting NUMA (non-uniform memory access architecture) domains in computer system of complex topologic structure |
| CN108776668A (en) * | 2018-05-04 | 2018-11-09 | 上海西井信息科技有限公司 | Path evaluation method, system, equipment and storage medium based on road-net node |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1435033A (en) * | 2000-03-15 | 2003-08-06 | 英佛西莫信息技术股份有限公司 | Method and system for communication of data via optimum data path in network |
| CN101547491A (en) * | 2009-04-15 | 2009-09-30 | 电子科技大学 | Routing method for mobile ad hoc network system |
| US8477601B2 (en) * | 2009-02-10 | 2013-07-02 | Hitachi, Ltd. | Network management station, network control system, and network management method |
-
2015
- 2015-01-28 CN CN201510044898.7A patent/CN104579963B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1435033A (en) * | 2000-03-15 | 2003-08-06 | 英佛西莫信息技术股份有限公司 | Method and system for communication of data via optimum data path in network |
| US8477601B2 (en) * | 2009-02-10 | 2013-07-02 | Hitachi, Ltd. | Network management station, network control system, and network management method |
| CN101547491A (en) * | 2009-04-15 | 2009-09-30 | 电子科技大学 | Routing method for mobile ad hoc network system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105827453A (en) * | 2016-04-25 | 2016-08-03 | 浪潮电子信息产业股份有限公司 | Method for setting NUMA (non-uniform memory access architecture) domains in computer system of complex topologic structure |
| CN108776668A (en) * | 2018-05-04 | 2018-11-09 | 上海西井信息科技有限公司 | Path evaluation method, system, equipment and storage medium based on road-net node |
| CN108776668B (en) * | 2018-05-04 | 2020-11-17 | 上海西井信息科技有限公司 | Path estimation method, system, equipment and storage medium based on road network nodes |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104579963B (en) | 2017-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20160349993A1 (en) | Data-driven ceph performance optimizations | |
| CN104298541A (en) | Data distribution algorithm and data distribution device for cloud storage system | |
| US20220210030A1 (en) | SYNTHESIS OF A NETWORK-ON-CHIP (NoC) USING PERFORMANCE CONSTRAINTS AND OBJECTIVES | |
| WO2019000340A1 (en) | Network topology structure mapping method and device, terminal and storage medium | |
| CN101588518A (en) | A kind of transmission network topological structure safety analytical method and realization system | |
| CN103236989B (en) | Buffer control method in a kind of content distributing network, equipment and system | |
| CN111290699B (en) | Data migration method, device and system | |
| CN105681153A (en) | Virtual network mapping method and device | |
| CN102780628B (en) | On-chip interconnection network routing method oriented to multi-core microprocessor | |
| CN105718221A (en) | Data storage method, device and system | |
| CN108259195A (en) | The determining method and system of the coverage of anomalous event | |
| CN115048254A (en) | Simulation test method, system, equipment and readable medium of data distribution strategy | |
| CN106383826A (en) | Database checking method and apparatus | |
| CN104579963A (en) | Method and device for optimizing routes of nodes | |
| CN113835823A (en) | Resource scheduling method and device, electronic equipment and computer readable storage medium | |
| CN104283966A (en) | Data distribution algorithm and device of cloud storage system | |
| CN105302838A (en) | Classification method as well as search method and device | |
| CN108075967A (en) | A kind of link choosing method and device | |
| CN109271438A (en) | A kind of data bank access method and its system | |
| CN201467146U (en) | Transmission network topological structure safety analysis system | |
| CN114285783B (en) | Route diffusion simulation method and device based on multiple matrixes | |
| CN109688758A (en) | For determining method, apparatus, electronic equipment and the medium of data center's failure | |
| CN114237985A (en) | Method for repairing failed memory block in erasure code memory system and related device | |
| Zhang et al. | Predicted congestion using a density-based fast neural network algorithm in global routing | |
| CN110166362B (en) | Service function graph low-delay mapping method based on node screening |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |