CN106453114B - Flow distribution method and device - Google Patents

Flow distribution method and device Download PDF

Info

Publication number
CN106453114B
CN106453114B CN201610890086.9A CN201610890086A CN106453114B CN 106453114 B CN106453114 B CN 106453114B CN 201610890086 A CN201610890086 A CN 201610890086A CN 106453114 B CN106453114 B CN 106453114B
Authority
CN
China
Prior art keywords
flow
traffic
output port
port
function
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201610890086.9A
Other languages
Chinese (zh)
Other versions
CN106453114A (en
Inventor
刘昱
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201610890086.9A priority Critical patent/CN106453114B/en
Publication of CN106453114A publication Critical patent/CN106453114A/en
Application granted granted Critical
Publication of CN106453114B publication Critical patent/CN106453114B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/80—Actions related to the user profile or the type of traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control

Abstract

The invention discloses a flow distribution method and a device, comprising the following steps: the mode selection module is used for selecting a preset flow distribution mode, and the flow distribution mode is provided with an output port selection function, a flow regulation function and a session granularity selection function; the parameter input module is used for inputting configuration parameters corresponding to the flow distribution mode; the port data acquisition module is used for acquiring flow data of the input port and the output port in real time and predicting future flow data of the input port according to the acquired flow data; the function calculation module is used for executing an output port selection function, a flow regulation function and a session granularity selection function according to the configuration parameters, the flow data of the input port and the output port and the flow data predicted in the future of the input port; the distribution module is used for distributing the flow from the input port to the output port according to the function execution result. By the scheme disclosed by the invention, the utilization rate of the port bandwidth is improved, and the network experience of a user is improved.

Description

Flow distribution method and device
Technical Field
The present invention relates to the field of network communications, and in particular, to a traffic distribution method and apparatus.
Background
In a network of a data center or a computer room, a traffic distribution device is generally arranged between network domains, such as an external network outlet, to perform the function of outlet/inlet traffic distribution. Generally speaking, there may be multiple traffic outlets, such as operator 1 outlet, operator 2 outlet, operator 3 outlet, due to differences and asymmetries in reliability, content buffering, cost, and size and type of uplink and downlink traffic. Due to different conditions of lease cost, bandwidth size, uplink and downlink traffic size, reliability and content caching of the outlets, traffic distribution equipment is often required to specifically distribute different traffic to different outlets. The traditional scheme is to use technologies such as policy routing to select a port of a traffic outlet, but because the mode of the traditional technical scheme such as measurement routing is relatively fixed, the granularity of traffic selection is large, and traffic with different granularities cannot be dynamically selected according to the change of demands and conditions to be distributed to the optimal outlet, the device cannot flexibly and efficiently complete the function of traffic distribution, and similar problems also exist in a backward traffic distribution method, which are not described herein. Especially, nowadays, the service types of network traffic are continuously increased, and the awareness of network users on the network quality and experience is continuously improved, so that the operation, management and maintenance parties of the network have to put forward higher requirements on traffic distribution equipment.
Disclosure of Invention
In view of this, the present invention provides a traffic allocation method and apparatus, which implement dynamic and flexible allocation of network traffic by using an SDN (software defined network) technology, improve the utilization rate of port bandwidth, and improve user experience.
The flow distribution device provided by the embodiment of the invention comprises a mode selection module, a parameter input module, a port data acquisition module, a function calculation module and a distribution module, wherein the mode selection module is used for selecting a preset flow distribution mode, and the flow distribution mode is provided with an output port selection function, a flow regulation function and a session granularity selection function; the parameter input module is used for inputting the configuration parameters corresponding to the flow distribution mode; the port data acquisition module is used for acquiring flow data of the input port and the output port in real time and predicting future flow data of the input port according to the acquired flow data; the function calculation module is used for executing the output port selection function, the flow regulation function and the session granularity selection function according to the configuration parameters, the input port and output port flow data and future predicted flow data of the input port; the distribution module is used for distributing the flow from the input port to the output port according to the function execution result. The flow in the invention is composed of sessions with different granularities, namely, the session selected by the session granularity selection function is the flow, and the flow in the patent can be called as the session with different granularities without special statement and is not repeatedly declared.
Preferably, the traffic allocation pattern includes a port priority pattern, and the configuration parameters in the port priority pattern include: a traffic bandwidth threshold and a total bandwidth for each output port; a priority value assigned to each output port.
Preferably, the traffic distribution pattern includes a weighted load pattern, and the configuration parameters in the weighted load pattern include: a traffic bandwidth threshold and a total bandwidth for each output port; each output port is assigned a weight value.
Preferably, the traffic allocation pattern includes a user and service type pattern, and the configuration parameters in the user and service type pattern include: a traffic bandwidth threshold and a total bandwidth for each output port; the user category attribute value assigned to each output port; a traffic type attribute value assigned to each output port.
Preferably, the output port selection function is used to select a suitable output port for the traffic, the traffic adjustment function is used to adjust the traffic allocated to the output port in real time to meet the requirement of the selected traffic allocation mode, and the session granularity selection function is used to select a traffic with a suitable granularity to optimally meet the requirement of traffic allocation.
In another embodiment of the present invention, a traffic management method is provided, including: selecting a preset flow distribution mode, wherein the flow distribution mode is provided with an output port selection function, a flow regulation function and a session granularity selection function; inputting configuration parameters corresponding to the flow distribution mode; acquiring flow data of an input port and an output port in real time; predicting future flow data of an input port according to the acquired flow data; executing the output port selection function, the flow regulation function and the session granularity selection function according to the configuration parameters, the input port and output port flow statistical data and the predicted future flow data of the input port; and distributing the flow from the input port to the output port according to the function execution result. The flow in the invention is composed of sessions with different granularities, namely, the session selected by the session granularity selection function is the flow, and the flow in the patent can be called as the session with different granularities without special statement and is not repeatedly declared.
Preferably, the traffic allocation pattern includes a port priority pattern, and the configuration parameters in the port priority pattern include: a traffic bandwidth threshold and a total bandwidth for each output port; a priority value assigned to each output port.
Preferably, the traffic distribution pattern includes a weighted load pattern, and the configuration parameters in the weighted load pattern include: a traffic bandwidth threshold and a total bandwidth for each output port; each output port is assigned a weight value.
Preferably, the traffic allocation pattern includes a user and service type pattern, and the configuration parameters in the user and service type pattern include: a traffic bandwidth threshold and a total bandwidth for each output port; the user category attribute value assigned to each output port; a traffic type attribute value assigned to each output port.
Preferably, the output port selection function is used to select a suitable output port for the traffic, the traffic adjustment function is used to adjust the traffic allocated to the output port in real time to meet the requirement of the selected traffic allocation mode, and the session granularity selection function is used to select a traffic with a suitable granularity to optimally meet the requirement of traffic allocation.
The flow distribution method and the flow distribution device enable the flow in the SDN to be dynamically distributed, improve the utilization rate of port bandwidth, improve the network experience of users, save the cost of purchasing extra bandwidth, and enable the network to be more flexible and efficient.
The invention is described in detail below with reference to the drawings and specific examples, but the invention is not limited thereto.
Drawings
Fig. 1 is a diagram of an application environment of an embodiment of a flow distribution device 10 according to the present invention.
Fig. 2 is a functional block diagram of an embodiment of a flow distribution device 10 according to the present invention.
Fig. 3 is a functional block diagram of another embodiment of the flow distribution apparatus 10 of the present invention.
Fig. 4 is a flowchart of an embodiment of a traffic distribution method according to the present invention.
Description of the main elements
Flow distribution device 10
SDN controller 1
SDN network device 2
Mode selection module 100
Parameter input module 102
Port data acquisition module 104
Function calculation module 106
Dispensing Module 108
Memory 110
Processor 112
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a diagram of an application environment of an embodiment of a flow distribution device 10 according to the present invention. The traffic distribution device 10 is located in an SDN controller 1, and the SDN controller 1 is connected to control an SDN network device 2 (such as an SDN switch) in an entire SDN network, where n input ports (n is a non-zero positive integer) and m output ports (m is a non-zero positive integer) exist in the SDN network device 2. In the present embodiment, the flow rate distribution device 10 can dynamically distribute the flow rate to the output port according to the flow rate of the input port and the preset conditions.
Fig. 2 is a functional block diagram of an embodiment of a flow distribution device 10 according to the present invention. The flow distribution device 10 includes a mode selection module 100, a parameter input module 102, a port data acquisition module 104, a function calculation module 106, and a distribution module 108.
The mode selection module 100 is configured to select a preset traffic distribution mode, where the traffic distribution mode has an output port selection function, a traffic adjustment function, and a session granularity selection function. In this embodiment, the mode selection module 100 selects a preset flow allocation mode, which may be actively selected by a user or triggered by other environmental factors, such as network congestion, time change or other conditions.
The parameter input module 102 is configured to input a configuration parameter corresponding to the flow distribution mode. Each flow allocation pattern corresponds to a set of configuration parameters, so that the allocation of the flow in the SDN network device 2 matches the requirements of the corresponding flow allocation pattern.
In this embodiment, the preset traffic allocation mode may be a port priority mode, and as shown in table-1, the configuration parameters in the port priority mode include: traffic bandwidth threshold and total bandwidth per output port, e.g. output port OUT1、OUT2The bandwidth threshold/total bandwidth of the system is respectively 80M/100M and 16M/20M; priority value assigned to each output port, e.g. output port OUT1、OUT2The priorities of (1) and (2) are respectively.
OUT1 OUT2 OUTi OUTm
Threshold/total bandwidth 80M/100M 16M/20M ...... 8M/10M
Port priority
1 2 ...... n
TABLE-1
In this embodiment, the preset traffic distribution mode may also be a weighted load mode, and as shown in table-2, the configuration parameters in the weighted load mode include: traffic bandwidth threshold and total bandwidth per output port, e.g. output port OUT1、OUT2The bandwidth threshold/total bandwidth of the system is respectively 80M/100M and 16M/20M; weight value assigned to each output port, e.g. output port OUT1、OUT2The priorities of (1) and (2) are 0.6 and 0.1, respectively.
OUT1 OUT2 OUTi OUTm
Threshold/total bandwidth 80M/100M 16M/20M ...... 8M/10M
Port weighting values 0.6 0.1 ...... 0.1
TABLE-2
In this embodiment, the preset traffic allocation mode may also be a user and service type mode, where the configuration parameters in the user and service type mode include: traffic bandwidth threshold and total bandwidth per output port, e.g. output port OUT1、OUT2The bandwidth threshold/total bandwidth of the system is respectively 80M/100M and 16M/20M; user class attribute value assigned to each output port, e.g. output port OUT1、OUT2User category attribute manager, research and development group; service type attribute value assigned to each output port, e.g. output port Out1、Out2The type of the traffic is http/smtp, http/smtp.
Figure BDA0001128374990000051
Figure BDA0001128374990000061
TABLE-3
The port data obtaining module 104 is configured to obtain flow statistics data of the flow input port and the flow output port in real time, and predict future flow data of the input port according to the obtained flow data.
The function calculating module 106 is configured to execute the output port selecting function, the traffic adjusting function, and the session granularity selecting function according to the configuration parameter, the input port traffic data, the output port traffic data, and the predicted future traffic data of the input port. In this embodiment, different traffic distribution modes correspond to different output port selection functions, traffic adjustment functions, and session granularity selection functions, and specifically, a port priority mode and a weighted load mode are taken as examples for description.
1. Port priority mode:
1.1 Port selection function F1 (X)1，R1) For selecting an egress for the new session. Wherein X1For a current certain outlet OUTi(i is not less than 0 and not more than m) flow data, X2Predicting traffic for the current session, R1For parameters in an outlet priority order list set by a user in a port priority mode, the function searches a first output port j _ F1 (j is more than or equal to 0 and less than or equal to m) of which the current flow does not exceed the upper limit from the most-preferred outlet in sequence, returns to the output port j _ F1, and calculates the difference △ X _ F1 between the current flow of the port and the upper limit of the flow;
1.2 Session granularity selection function F2(△ X, X)2) The output port j _ F1j selected by F1 is imported with the new session selected as appropriate. Wherein X2The method comprises the steps of predicting flow for a current session, selecting a new session with proper granularity through a difference △ X between the current flow of a port and the upper limit flow of the port, and freely selecting the most proper session granularity according to △ X if a user has no special requirement, wherein the granularity is used for classifying messages, the messages can be classified into different types and sent to a required outlet to realize flow distribution;length of message: length, unit bit.
1.3 flow regulating function F3 (X)1，R1) Is used to dynamically adjust the output port traffic allocation. Wherein X1Is an outlet OUTiCurrent flow data of R1For the parameters in the exit priority order list set by the user in port priority mode, the function finds the first exit i with non-zero current traffic from the lowest priority exit (the exit with non-zero traffic is found from low to high in priority from the lowest priority exit), if there is a exit OUTiHigher priority egress traffic is not capped, OUTiThe session in (1) is taken out as F2(△ X, X)2) X in (1)2The new session in (1) is preferentially allocated to the egress that does not reach the upper limit of the traffic.
2. Weighted load mode:
2.1 Port selection function F4 (X)1，X2，R2) For selecting the minimum variance outlet, where X1For outlet flow data, X2Predicting traffic data for the current session, R2Allocating a proportion table for the flow set by the user for each outlet in the weighted load mode; for each outlet i (0. ltoreq. i. ltoreq.m) for which the distribution ratio is non-zero, calculate:
the proportion r of the current flow of the outlet ii(ri＝X1i/X1allWherein X is1allIs the total outlet flow) to a set ratio RiSquare of deviation of (d): e0i＝[(ri-Ri)/Ri]2(Explanation: calculation per port);
egress i current traffic plus current session expected traffic s (s ═ X)2/(X1all+X2) After that) to a set ratio RiSquare of deviation of (e 1)i＝[(ri+s-Ri)/Ri]2(Explanation: calculation per port);
△ e is calculated for each porti＝e1i-e0iA value of (d);
if e1i-e0iOutlet of smallest (may be negative) valuei does not exceed the preset upper flow limit (r)i+s-Ri<0) Return to egress i (i.e. this session X)2The traffic of (2) is distributed to the i port);
e1i-e0i＝[s-2(Ri-ri)]s/Ri，rithe closer to RiThe larger the value calculation, the larger the resistance e1 of the porti-e0iWhen it is negative, i.e. Ri-ri<s/2, i.e. when the current residual proportion is less than half of the proportion to be distributed, s is added and then exceeds the set value, if X is added at the moment2The i-port threshold will be exceeded, so the description as in function F5 can pass through e1i-e0iSelecting the appropriate X2Performing iterative calculation (predicting the flow of a new session with a certain granularity) to obtain the optimal flow introduction effect;
2.2 Session granularity selection function F5 (X)2，△ei) Through △ ei＝e1i-e0iSelecting appropriate session granularity traffic X2Assigned to the corresponding port, F4 and F5 will be adjusted several times to calculate the flow distribution after selecting outlet i in F4 to be closer to the flow requirement in this mode.
2.3 flow regulating function F6 (X)1，R2) For regulating outlet distribution, X1As outlet flow data, R2And searching the outlet i with the current flow rate accounting for the maximum proportion exceeding the set proportion for the flow rate distribution proportion set by the user for each outlet in the weighted load mode, and taking the conversation in the outlet i out to call the function F4 for redistribution.
The distribution module 108 is configured to distribute traffic according to the function execution result. In this embodiment, after the function calculation module 106 performs the function calculation process, the flow allocation of each port can be adjusted in real time according to the calculation result, so that the flow of a certain output port meets the requirement of the selected flow allocation mode.
Fig. 3 is a functional block diagram of another embodiment of the flow distribution apparatus 10 of the present invention. The flow distribution device 10 includes a mode selection module 100, a parameter input module 102, a port data acquisition module 104, a function calculation module 106, a distribution module 108, a memory 110, and a processor 112, where the mode selection module 100, the parameter input module 102, the port data acquisition module 104, the function calculation module 106, and the distribution module 108 are program codes, exist in the memory 110 in the form of functional modules, and are processed by the processor 112 to implement corresponding functions.
Fig. 4 is a flowchart of an embodiment of a traffic distribution method according to the present invention.
In step S400, the mode selection module 100 is configured to select a preset traffic distribution mode, where the traffic distribution mode has an output port selection function, a traffic adjustment function, and a session granularity selection function. In this embodiment, the mode selection module selects the preset flow allocation mode, which may be triggered by the active selection of the user, or may be triggered by other environmental factors, such as network congestion.
In step S402, the parameter input module 102 is configured to input a configuration parameter corresponding to the flow distribution mode. Each traffic distribution mode corresponds to a set of configuration parameters, so that the distribution of traffic in the SDN network device 2 matches the requirement of the response traffic distribution mode as much as possible.
In this embodiment, the preset traffic allocation mode may be a port priority mode, and as shown in table-1 above, the configuration parameters in the port priority mode include: traffic bandwidth threshold and total bandwidth per output port, e.g. output port OUT1、OUT2The threshold value/total bandwidth of (1) is respectively 80M/100M and 16M/20M; the priority value assigned to each output port, such as the priority of output ports OUT1, OUT2, is 1, 2, respectively.
In this embodiment, the preset traffic distribution pattern may be a weighted load pattern, as shown in table-2, where the configuration parameters in the weighted load pattern include: traffic bandwidth threshold and total bandwidth per output port, e.g. output port OUT1、OUt2The threshold value/total bandwidth of (1) is respectively 80M/100M and 16M/20M; weight value assigned to each output port, e.g. output port OUT1、OUT2The priorities of (1) and (2) are 0.6 and 0.1, respectively.
In this embodiment, the preset traffic allocation mode may be a user and service type mode, and the configuration parameters in the user and service type mode include: traffic bandwidth threshold and total bandwidth per output port, e.g. output port OUT1、OUT2The threshold value/total bandwidth of (1) is respectively 80M/100M and 16M/20M; user class attribute value assigned to each output port, e.g. output port OUT1、OUT2User category attribute manager, research and development group; the value of a traffic type attribute assigned to each output port, e.g. output port OUT1、OUT2The type of the traffic is http/smtp, http/smtp.
In step S404, the port data obtaining module 104 is configured to obtain flow statistics data of the flow input port and the flow output port in real time, and predict future flow data of the input port according to the obtained flow data.
In step S406, the function calculating module 106 is configured to execute the output port selecting function, the traffic adjusting function, and the session granularity selecting function according to the configuration parameter, the input port traffic data, the output port traffic data, and the predicted future traffic data of the input port. In this embodiment, different traffic distribution modes correspond to different output port selection functions, traffic adjustment functions, and session granularity selection functions, and specifically, a port priority mode and a weighted load mode are taken as examples for description.
1. Port priority mode:
1.1 Port selection function F1 (X)1，R1) For selecting an egress for the new session. Wherein X1For a current certain outlet OUTi(m is not less than i is not more than m) flow data, X2Predicting traffic for the current session, R1For parameters in an outlet priority order list set by a user in a port priority mode, the function searches a first output port j _ F1 (j is more than or equal to 0 and less than or equal to m) of which the current flow does not exceed the upper limit from the most-preferred outlet in sequence, returns to the output port j _ F1, and calculates the difference △ X _ F1 between the current flow of the port and the upper limit of the flow;
1.2 Session granularity selection function F2(△ X, X)2) And the output port j _ F1 selected by the F1 is imported with the new session selected by the F1. Wherein X2Predict traffic for the current session, through the port the current traffic is △ X different from its upper limit traffic, select a new session with the appropriate granularity, and freely select the most appropriate session granularity according to △ X if the user has no special requirement, wherein the granularity is described as above.
1.3 flow regulating function F3 (X)1，R1) Is used to dynamically adjust the output port traffic allocation. Wherein X1Is an outlet OUTiCurrent flow data of R1For the parameters in the exit priority order list set by the user in port priority mode, the function finds the first exit i with non-zero current traffic from the lowest priority exit (the exit with non-zero traffic is found from low to high in priority from the lowest priority exit), if there is a exit OUTiHigher priority egress traffic is not capped, OUTiThe session in (1) is taken out as F2(△ X, X)2) X in (1)2The new session in (1) is preferentially allocated to the egress that does not reach the upper limit of the traffic.
2. Weighted load mode:
2.1 function F4 (X)1，X2，R2) For selecting the minimum variance outlet, where X1For outlet flow data, X2Predicting traffic data for the current session, R2Allocating a proportion table for the flow set by the user for each outlet in the weighted load mode; for each outlet i (0. ltoreq. i. ltoreq.m) for which the distribution ratio is non-zero, calculate:
the proportion r of the current flow of the outlet ii(ri＝X1i/X1allWherein X is1allIs the total outlet flow) to a set ratio RiSquare of deviation of (d): e0i＝[(ri-Ri)/Ri]2(Explanation: calculation per port);
egress i current traffic plus current session expected traffic s (s ═ X)2/(X1all+X2) After) is pairedSetting the ratio RiSquare of deviation of (e 1)i＝[(ri+s-Ri)/Ri]2(Explanation: calculation per port);
calculate e1 for each porti-e0iA value of (d);
if e1i-e0iThe flow rate of the outlet i with the smallest value (which may be negative) does not exceed the preset upper flow rate limit (r)i+s-Ri<0) Return to egress i (i.e. this session X)2The traffic of (2) is distributed to the i port);
e1i-e0i＝[s-2(Ri-ri)]s/Ririthe closer to RiThe larger the value calculation, the larger the resistance e1 of the porti-e0iWhen it is negative, i.e. Ri-ri<s/2, i.e. when the current residual proportion is less than half of the proportion to be distributed, s is added and then exceeds the set value, if X is added at the moment2The i-port threshold will be exceeded, so the description as in function F5 can pass through e1i-e0iSelecting the appropriate X2Performing iterative calculation (predicting the flow of a new session with a certain granularity) to obtain the optimal flow introduction effect;
2.2 Session granularity selection function F5 (X)2，△ei) Through △ ei＝e1i-e0iSelecting appropriate session granularity traffic X2Assigned to the corresponding port, F4 and F5 will be adjusted several times to calculate the flow distribution after selecting outlet i in F4 to be closer to the flow requirement in this mode.
2.3 flow regulating function F6 (X)1，R2) For regulating outlet distribution, X1As outlet flow data, R2And searching the outlet i with the current flow rate accounting for the maximum proportion exceeding the set proportion for the flow rate distribution proportion set by the user for each outlet in the weighted load mode, and taking the conversation in the outlet i out to call the function F4 for redistribution.
In step S408, the allocating module 108 is configured to allocate traffic according to the function execution result. In this embodiment, after the function calculation module 106 performs the function calculation process, the flow allocation of each port can be adjusted in real time according to the calculation result, so that the flow of a certain output port meets the requirement of the selected flow allocation mode.
In addition, the invention describes a traffic distribution method and device in a certain direction, and the distribution of data traffic in another direction (return direction) can also be operated in the same way, and is similar to the description of the invention in the case of properly adding optional characteristics such as round-trip paths, and the description is not repeated.
By executing the traffic distribution method through the traffic distribution device 10, the traffic in the SDN network is dynamically distributed, the utilization rate of the port bandwidth is improved, the network experience of a user is improved, the cost for purchasing additional bandwidth is saved, and the network is more flexible and efficient.
The above-described embodiments do not limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (8)

1. A traffic distribution method is applied to an SDN controller and is characterized by comprising the following steps:
selecting a preset flow distribution mode, wherein the flow distribution mode is provided with an output port selection function, a flow regulation function and a session granularity selection function, the output port selection function is used for selecting a proper output port for flow, the flow regulation function is used for regulating the flow of a certain output port in real time to enable the flow to meet the requirement of the selected flow distribution mode, and the session granularity selection function is used for selecting a session with proper granularity to be output to a proper output port to achieve the flow distribution requirement which is most consistent with the flow distribution mode;
inputting configuration parameters corresponding to the flow distribution mode;
acquiring input port flow data and output port flow data in real time;
predicting future flow data of the input port according to the acquired input port flow data and the acquired output port flow data;
executing the output port selection function, the traffic regulation function and the session granularity selection function according to the configuration parameters, the input port traffic data, the output port traffic data and the future traffic data of the input port; and
and carrying out flow distribution according to a function execution result, traversing the current flow nonzero flow output ports by the flow regulation function based on the sequence of the priority of the output ports from low to high, and taking the session in the flow nonzero flow output ports as the session selected by the session granularity selection function if the flow of the output port with the higher priority of the flow nonzero flow output ports is less than the upper limit value.
2. The traffic distribution method of claim 1, wherein the traffic distribution pattern comprises a port priority pattern, and the configuration parameters in the port priority pattern comprise: a traffic bandwidth threshold and a total bandwidth for each output port;
a priority value assigned to each output port.
3. The traffic distribution method of claim 1, wherein the traffic distribution pattern comprises a weighted load pattern, and the configuration parameters in the weighted load pattern comprise:
a traffic bandwidth threshold and a total bandwidth for each output port; each output port is assigned a weight value.
4. The traffic distribution method according to claim 1, wherein the traffic distribution pattern comprises a user and service type pattern, and the configuration parameters in the user and service type pattern comprise:
a traffic bandwidth threshold and a total bandwidth for each output port;
the user category attribute value assigned to each output port;
a traffic type attribute value assigned to each output port.
5. A flow distribution device applied to an SDN controller is characterized by comprising:
the system comprises a mode selection module, a traffic distribution module and a traffic control module, wherein the mode selection module is used for selecting a preset traffic distribution mode, the traffic distribution mode is provided with an output port selection function, a traffic regulation function and a session granularity selection function, the output port selection function is used for selecting a proper output port for traffic, the traffic regulation function is used for regulating the traffic of a certain output port in real time to enable the certain output port to meet the requirement of the selected traffic distribution mode, and the session granularity selection function is used for selecting a session with proper granularity to be output to a proper output port to achieve the traffic distribution requirement which is most consistent with the traffic distribution mode;
the parameter input module is used for inputting the configuration parameters corresponding to the flow distribution mode;
the port data acquisition module is used for acquiring input port flow data and output port flow data in real time and predicting future flow data of the input port according to the acquired input port flow data and output port flow data;
a function calculation module, configured to execute the output port selection function, the traffic regulation function, and the session granularity selection function according to the configuration parameter, the input port traffic data, the output port traffic data, and the future traffic data of the input port; and
and the distribution module is used for carrying out flow distribution according to a function execution result, the flow regulation function traverses the flow non-zero output ports with non-zero current flow based on the sequence of the priority of the output ports from low to high, and if the flow of the output port with higher priority of the flow non-zero output ports is smaller than an upper limit value, the session in the flow non-zero output ports is used as the session selected by the session granularity selection function.
6. The traffic distribution apparatus of claim 5, wherein the traffic distribution pattern comprises a port priority pattern, and wherein the configuration parameters in the port priority pattern comprise:
a traffic bandwidth threshold and a total bandwidth for each output port;
a priority value assigned to each output port.
7. The traffic distribution apparatus of claim 5, wherein the traffic distribution pattern comprises a weighted load pattern, and wherein the configuration parameters in the weighted load pattern comprise:
a traffic bandwidth threshold and a total bandwidth for each output port;
each output port is assigned a weight value.
8. The traffic distribution apparatus of claim 5, wherein the traffic distribution pattern comprises a user and traffic type pattern, and the configuration parameters in the user and traffic type pattern comprise:
a traffic bandwidth threshold and a total bandwidth for each output port;
the user category attribute value assigned to each output port;
a traffic type attribute value assigned to each output port.
CN201610890086.9A 2016-10-11 2016-10-11 Flow distribution method and device Active CN106453114B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610890086.9A CN106453114B (en) 2016-10-11 2016-10-11 Flow distribution method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610890086.9A CN106453114B (en) 2016-10-11 2016-10-11 Flow distribution method and device

Publications (2)

Publication Number Publication Date
CN106453114A CN106453114A (en) 2017-02-22
CN106453114B true CN106453114B (en) 2020-03-17

Family

ID=58173649

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610890086.9A Active CN106453114B (en) 2016-10-11 2016-10-11 Flow distribution method and device

Country Status (1)

Country Link
CN (1) CN106453114B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106911581B (en) * 2017-02-28 2020-06-23 联想(北京)有限公司 Transmission method, device and terminal
CN107689901B (en) * 2017-11-13 2020-12-18 锐捷网络股份有限公司 Method and device for monitoring traffic message flow
CN109547343B (en) * 2019-01-04 2020-09-18 网宿科技股份有限公司 Traffic scheduling method and system
CN112486871B (en) * 2020-11-25 2023-06-13 海光信息技术股份有限公司 Routing method and system for on-chip bus

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1913488A (en) * 2004-12-29 2007-02-14 阿尔卡特公司 Predictive congestion management in a data communications switch using traffic and system statistics
CN105162698A (en) * 2015-10-10 2015-12-16 浪潮(北京)电子信息产业有限公司 Method and device for cloud server to adjust SDN network paths based on memory model
CN105721577A (en) * 2016-02-15 2016-06-29 安徽大学 Server load balancing method for software defined network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1913488A (en) * 2004-12-29 2007-02-14 阿尔卡特公司 Predictive congestion management in a data communications switch using traffic and system statistics
CN105162698A (en) * 2015-10-10 2015-12-16 浪潮(北京)电子信息产业有限公司 Method and device for cloud server to adjust SDN network paths based on memory model
CN105721577A (en) * 2016-02-15 2016-06-29 安徽大学 Server load balancing method for software defined network

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
IMPLEMENTATION OF SMART-OSPF IN HYBRID SOFTWARE-DEFINED NETWORK;Yasunori Nakahodo等;《Proceedings of 2014 4th IEEE International Conference on Network Infrastructure and Digital Content》;20140919;全文 *
SDN-based Solution of Path Restoration for Smart Grids;Ma Wei Zhe等;《4th International Conference on Computer, Mechatronics, Control and Electronic Engineering (ICCMCEE 2015)》;20150928;全文 *

Also Published As

Publication number Publication date
CN106453114A (en) 2017-02-22

Similar Documents

Publication Publication Date Title
US10129043B2 (en) Apparatus and method for network flow scheduling
CN106453114B (en) Flow distribution method and device
CN109600262A (en) Resource self-configuring and self-organization method and device in URLLC transmission network slice
RU2677373C1 (en) Fractal telecommunication traffic transmission quality increasing method
CN106341346A (en) Routing algorithm of guaranteeing QoS in data center network based on SDN
US9705804B2 (en) Opportunistic wireless resource utilization using dynamic traffic shaping
CN109218216B (en) Link aggregation flow distribution method, device, equipment and storage medium
CN110248417A (en) The resource allocation methods and system of uplink communication business in a kind of electric power Internet of Things
CN106059942A (en) Traffic control method based on load prediction in SDN network
US11509566B2 (en) Shaping outgoing traffic of network packets in a network management system
Wang et al. Control link load balancing and low delay route deployment for software defined networks
CN106027288A (en) Communication traffic prediction method for distribution line information monitoring service
Farmanbar et al. Traffic engineering for software-defined radio access networks
CN114268537B (en) Deterministic network-oriented network slice generation and dynamic configuration system and method
WO2014070937A1 (en) System and methods to achieve optimum efficiency-jain fairness in wireless systems
CN107995121B (en) Method for counting flow in software defined network based on wildcard
Manfredi Decentralized queue balancing and differentiated service scheme based on cooperative control concept
CN104902570B (en) A kind of dynamics of channels configuration method and device
US11924061B2 (en) Required communication quality estimation apparatus, required communication quality estimation method and program
Guillemin et al. Controlling impatience in cellular networks using QoE-aware radio resource allocation
Daneshvar Farzanegan et al. A scheduling algorithm for bursty traffic: Controlling of service rate and burst
Bonald et al. The multi-source model for dimensioning data networks
G∤ ąbowski et al. Simulation studies of communication systems with mutual overflows and threshold mechanisms
Boroujeny et al. Traffic workload envelope for network performance guarantees with multiplexing gain
Lebedenko et al. A queue management model on the network routers using optimal flows aggregation

Legal Events

Date Code Title Description
C06 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