CN107248959B - Flow optimization method and device - Google Patents
Flow optimization method and device Download PDFInfo
- Publication number
- CN107248959B CN107248959B CN201710527008.7A CN201710527008A CN107248959B CN 107248959 B CN107248959 B CN 107248959B CN 201710527008 A CN201710527008 A CN 201710527008A CN 107248959 B CN107248959 B CN 107248959B
- Authority
- CN
- China
- Prior art keywords
- network
- network traffic
- time period
- users
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- H04L47/10—Flow control; Congestion control
-
- 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
- H04L47/20—Traffic policing
Abstract
The application discloses a traffic optimization method and a traffic optimization device, wherein the method comprises the steps of generating a corresponding relation between time and network traffic in a first time period based on historical network traffic information corresponding to different times in the first time period, generating a network traffic processing instruction based on the corresponding relation, and processing network traffic data of a user according to the network traffic processing instruction on the basis. Therefore, by using the scheme of the application, the network flow data can be processed based on the pre-generated corresponding relation between the time and the network flow in the first time period, the collection and calculation of the flow information and the formulation and issuing of the flow table are not required to be carried out in real time, and the pressure of the network core equipment in the network flow optimization can be effectively relieved.
Description
Technical Field
The invention belongs to the technical field of network flow control, and particularly relates to a flow optimization method and device.
Background
SDN (Software Defined Network), a forwarding platform performs message forwarding for controlling a forwarding separation type Network, that is, a control platform performs management control of the whole Network, and when Network traffic is congested, an SDN controller in the control platform performs unified traffic calculation and optimization.
In the current network traffic optimization scheme, forwarding devices in a forwarding platform generally acquire actual network traffic information (such as information on actual use conditions and congestion conditions of network traffic) in real time, an SDN controller performs unified calculation on acquired data, a flow table is updated based on calculation results and notified to the forwarding devices, and then the forwarding devices realize traffic optimization based on the updated flow table.
According to the network flow optimization scheme, the collection and calculation of flow information and the formulation and issuing of a flow table need to be carried out in real time, so that the pressure of SDN network core equipment, such as the pressure of an SDN controller, is increased. Accordingly, there is a need in the art to provide a traffic optimization scheme that can relieve SDN network core device stress.
Disclosure of Invention
In view of this, the present invention provides a traffic optimization method and apparatus, which aim to alleviate the pressure of network core devices in network traffic optimization.
Therefore, the invention discloses the following technical scheme:
a method of traffic optimization, comprising:
obtaining network flow information in a first time period; wherein the network traffic information comprises: historical network traffic information corresponding to different times during the first time period;
generating a corresponding relation between the time and the network flow in the first time period based on the network flow information in the first time period;
generating a network flow processing instruction based on the corresponding relation;
and processing the network traffic data of the user based on the network traffic processing instruction.
Preferably, the obtaining network traffic information in the first time period includes:
and obtaining historical network flow information corresponding to different types of network users at different times in a first time period.
Preferably, the generating a corresponding relationship between time and network traffic in the first time period based on the network traffic information in the first time period includes:
analyzing the use rules of the network traffic of the different types of network users at different times according to the historical network traffic information corresponding to the different types of network users at different times in the first time period;
and generating the corresponding relation between the time and the network flow for the different types of network users in the first time period according to the use rules of the different types of network users on the network flow at different times.
In the above method, preferably, the usage rule of the network traffic by the network user at different times at least includes: network users demand bandwidth of network traffic at different times;
generating a corresponding relationship between the time and the network traffic for the different types of network users in the first time period according to the usage rules of the different types of network users for the network traffic at different times, including:
generating a network forwarding flow table based on time according to the bandwidth requirements of different types of network users on network flow at different times; the network forwarding flow table at least comprises corresponding relations among different time, different types of network users and different network flow forwarding rules.
Preferably, in the method, the generating a network traffic processing instruction based on the correspondence includes:
according to the network forwarding flow table, matching corresponding network flow processing rules aiming at corresponding time for network users of corresponding types;
and generating a corresponding network flow processing instruction aiming at corresponding time for the corresponding type of network users according to the matched corresponding network flow processing rule.
A flow optimization device, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring network flow information in a first time period; wherein the network traffic information comprises: historical network traffic information corresponding to different times during the first time period;
a correspondence generating unit, configured to generate a correspondence between time and network traffic in the first time period based on the network traffic information in the first time period;
the instruction generating unit is used for generating a network flow processing instruction based on the corresponding relation;
and the processing unit is used for processing the network flow data of the user based on the network flow processing instruction.
The above apparatus, preferably, the obtaining unit is specifically configured to:
and obtaining historical network flow information corresponding to different types of network users at different times in a first time period.
Preferably, the device is configured to further include a correspondence generating unit, where the correspondence generating unit is specifically configured to:
analyzing the use rules of the network traffic of the different types of network users at different times according to the historical network traffic information corresponding to the different types of network users at different times in the first time period; and generating the corresponding relation between the time and the network flow for the different types of network users in the first time period according to the use rules of the different types of network users on the network flow at different times.
Preferably, the above apparatus, the usage rule of the network traffic by the network user at different times at least includes:
network users demand bandwidth of network traffic at different times;
the corresponding relationship generating unit generates, according to usage rules of network traffic by different types of network users at different times, a corresponding relationship between time and network traffic for the different types of network users in the first time period, and specifically includes:
generating a network forwarding flow table based on time according to the bandwidth requirements of different types of network users on network flow at different times; the network forwarding flow table at least comprises corresponding relations among different time, different types of network users and different network flow forwarding rules.
Preferably, the instruction generating unit of the apparatus is specifically configured to:
according to the network forwarding flow table, matching corresponding network flow processing rules aiming at corresponding time for network users of corresponding types; and generating a corresponding network flow processing instruction aiming at corresponding time for the corresponding type of network users according to the matched corresponding network flow processing rule.
According to the scheme, the traffic optimization method and the traffic optimization device provided by the application generate the corresponding relation between the time and the network traffic in the first time period based on the historical network traffic information corresponding to different times in the first time period, generate the network traffic processing instruction based on the corresponding relation, and process the network traffic data of the user according to the network traffic processing instruction on the basis. Therefore, by using the scheme of the application, the network flow data can be processed based on the pre-generated corresponding relation between the time and the network flow in the first time period, the collection and calculation of the flow information and the formulation and issuing of the flow table are not required to be carried out in real time, and the pressure of the network core equipment in the network flow optimization can be effectively relieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a traffic optimization method provided in an embodiment of the present application;
fig. 2 is another flowchart of a traffic optimization method provided in an embodiment of the present application;
fig. 3 is a schematic diagram illustrating a principle of implementing SDN network traffic optimization by using the solution of the present application according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a flow rate optimization device according to an embodiment of the present application.
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
An embodiment of the present application provides a traffic optimization method, which may be applied to a traffic optimization scenario of a network, for example, to be specifically applied to a core device of an SDN network for network traffic optimization, and with reference to a flowchart of a first embodiment of the traffic optimization method in the present application shown in fig. 1, the method may include the following steps:
In an actual traffic usage scenario, the usage of network traffic by users is often regular, for example, for enterprise users, the peak time of the usage of the network traffic is generally working time of working day (e.g., 8:00-12:00 and 12:00-18:00), and the non-working time of the non-working day and the working day is less usage of the network traffic.
Based on this, the application aims to analyze the usage rules of the user on the network traffic at different times in a certain time period through historical network traffic information when the user uses the network traffic at different times in the time period, and further perform time-based network traffic data processing on the user in the future time period based on the analysis of the usage rules, such as performing traffic data processing on the enterprise user based on a larger bandwidth in the working day and working time of the enterprise user.
The first time period may be a preset time period with a certain time length, such as but not limited to a day, two days, a week, a month, and so on.
The step of obtaining the network flow information in the first time period, namely obtaining the historical network flow information of the user corresponding to different times in the first time period, is realized to provide analysis basis for the usage rule of the network flow in the first time period.
Here, it should be noted that the network traffic information in the first time period obtained in this step is not limited to the network traffic information in only one first time period, for example, the first time period is 1 day, and the obtained network traffic information in the first time period is not limited to historical network traffic information in only different times in one day, but may be historical network traffic information in different times in multiple days by the user, more specifically, for example, historical network traffic information corresponding to different times of each day in the last 5 working days by the enterprise user, historical network traffic information corresponding to different times of each working day in each working day included in the last month, and the like, and the present application does not limit this.
102, generating a corresponding relation between the time in the first time period and the network traffic based on the network traffic information in the first time period.
On the basis of obtaining the network flow information in the first time period, namely obtaining historical network flow information of the user corresponding to different times in the first time period, analyzing the usage rule of the user on the network flow at different times in the first time period by using the obtained data as a basis, and further generating the corresponding relation between the different times and the network flow in the first time period for the user according to the rule result obtained by analyzing so as to provide a control basis for the subsequent network flow optimization control in the first time period.
And 103, generating a network flow processing instruction based on the corresponding relation.
Based on generating the correspondence between the time and the network traffic within the first time period for the user, a corresponding network traffic processing instruction may be generated based on the generated correspondence.
It should be noted that, since the correspondence is specifically a correspondence between time and network traffic, for example, an enterprise user corresponds to a network traffic with a higher bandwidth value during working time of a working day, and corresponds to a network traffic with a lower bandwidth value during non-working time, etc., a corresponding network traffic processing instruction generated according to the correspondence is also time-based, for example, a first network traffic processing instruction corresponding to a higher bandwidth value is generated for the enterprise user during working time, and a second network traffic processing instruction corresponding to a lower bandwidth value is generated during non-working time.
And 104, processing the network traffic data of the user based on the network traffic processing instruction.
Then, the network traffic data of the user may be processed according to the network traffic processing instruction, still taking the enterprise user as an example, during the working time of the working day, according to the first network traffic processing instruction, the required network traffic data processing may be performed for the enterprise user based on a higher network bandwidth, while during the non-working time, according to the second network traffic processing instruction, the required network traffic data processing may be performed for the enterprise user based on a lower network bandwidth.
According to the scheme, the traffic optimization method provided by the embodiment of the application generates the corresponding relation between the time and the network traffic in the first time period based on the historical network traffic information corresponding to different times in the first time period, generates the network traffic processing instruction based on the corresponding relation, and processes the network traffic data of the user according to the network traffic processing instruction on the basis. Therefore, by using the scheme of the application, the network flow data can be processed based on the pre-generated corresponding relation between the time and the network flow in the first time period, the collection and calculation of the flow information and the formulation and issuing of the flow table are not required to be carried out in real time, and the pressure of the network core equipment in the network flow optimization can be effectively relieved.
In another embodiment of the present application, referring to a flowchart of a second embodiment of a traffic optimization method according to the present application shown in fig. 2, in this embodiment, the traffic optimization method may be implemented by the following processing procedures:
Specifically, the usage rules of different types of users on the network are often different, for example, the peak time when an enterprise user uses the network traffic is generally the working time of a working day (e.g., 8:00-12: 001 and 3: 00-18:00), the remaining time uses the network traffic less, and the peak time when a campus user or a home user uses the network traffic is generally the evening (e.g., 18: 00-22: 00) and the weekend.
In order to implement network traffic optimization for different types of users, the embodiment first obtains historical network traffic information corresponding to different types of network users at different times in a first time period. For example, historical network traffic information corresponding to different types of network users in a first time period is obtained for enterprise users, campus users, home users, internet cafe users, and the like.
The first time period may be a preset time period with a certain time length, such as but not limited to a day, two days, a week, a month, and so on.
Here, it should be noted that the network traffic information in the first time period obtained in this step is not limited to the network traffic information in only one first time period, for example, the first time period is 1 day, and the obtained network traffic information in the first time period is not limited to historical network traffic information in only different times in one day, but may be historical network traffic information in different times in multiple days for corresponding types of users, more specifically, for example, historical network traffic information corresponding to different times of each working day of the last 5 working days for enterprise users, historical network traffic information corresponding to different times of each working day of the last month for campus users, and the like, and the present application does not limit this.
Taking SDN network traffic optimization as an example, referring to fig. 3, a schematic diagram of a principle for implementing SDN network traffic optimization by using the method of the present application is provided, where an SDN controller may formulate and issue a traffic collection task to a forwarding device through a network traffic collection module included in the SDN controller, and the formulated and issued traffic collection task includes collection content, a collection period, and the like. And a flow acquisition reporting module of the forwarding equipment acquires and reports flow information (reports the flow information to the SDN controller) based on an acquisition task issued by the SDN controller. In actual implementation, the collection task can be issued through the openflow protocol. It should be noted here that, since the collected traffic information is specifically used as an analysis basis for a usage rule of user network traffic, and further traffic optimization is achieved, so as to achieve optimization of current network traffic, the SDN network should complete a task of collecting the network traffic information in advance, for example, network traffic information collection of an enterprise user or a campus user may be performed a week in advance, so that historical data support is provided for current network traffic optimization through preprocessing work of data collection.
After obtaining the historical network traffic information corresponding to different types of network users at different times in the first time period, for example, after obtaining the historical network traffic information corresponding to different types of users, such as enterprise users, campus users, and home users, at different times in the first time period, the historical network traffic information may be counted and analyzed to analyze the usage rules of the network traffic by the different types of network users at different times.
The usage rules analyzed typically include at least the bandwidth requirements of different types of network users for network traffic at different times. In a real application scenario, a fixed type of network user tends to have a relatively stable bandwidth requirement for a sustained period of time, and thus, more specifically, the usage rules may include bandwidth requirements of different types of network users for network traffic at different time periods.
Referring to table 1 below, table 1 exemplarily provides information on usage rules of network traffic for three different users, namely, an enterprise, a campus, and an internet cafe.
TABLE 1
As can be seen from the above Table 1, the peak time of the network traffic of the enterprise user in the 1 day time period (assumed to be working days) is 8: 00-18:00, and there exists a bandwidth demand of about 70M/S, the peak time of the network traffic of the campus user in the 1 day time period is 18: 00-24: 00, and there exists a bandwidth demand of about 90M/S, and the peak time of the network traffic of the Internet cafe user in the 1 day time period is 24: 00-8: 00, and the sub-peak time is 18: 00-24: 00, and there exist bandwidth demands of about 80M/S and 50M/S, respectively.
Step 203, generating a corresponding relationship between the time and the network traffic for the different types of network users in the first time period according to the usage rules of the different types of network users on the network traffic at different times.
After analyzing the usage rules of different types of network users for network traffic at different times based on the historical network traffic information, the corresponding relationship between the time and the network traffic for the different types of network users in the first time period can be generated based on the usage rules obtained by the analysis.
In this embodiment, the correspondence between the time and the network traffic for the different types of network users in the first time period is generated in the form of a network forwarding flow table, specifically, in this embodiment, a network forwarding flow table based on time is generated according to bandwidth requirements of the different types of network users on the network traffic at different times; the network forwarding flow table at least comprises corresponding relations among different time, different types of network users and different network flow forwarding rules.
Taking the traffic usage rules of the three types of network users, i.e., enterprise, campus, and internet cafe, in table 1, for the time period of 8: 00-18:00, an entry of a network forwarding flow table mainly based on user a, i.e., an enterprise user, may be generated, and the entry is policy1, where in the entry corresponding to the time period of 8: 00-18:00, the enterprise user is configured with a bandwidth of about 70M/s, and the campus user and the internet cafe user are configured with bandwidths of about 2M/s and 20M/s, respectively. And generating a flow table entry Policy2 mainly aiming at the campus user in the time period of 18: 00-24: 00, and respectively configuring network bandwidths of about 2M/s, 90M/s and 50M/s for enterprise users, campus users and Internet cafe users in the entries corresponding to the time period of 18: 00-24: 00. And for the time period of 24: 00-8: 00, generating a flow table entry Policy3 mainly aiming at the Internet cafe users, and respectively configuring network bandwidths of about 0.5M/s, 1M/s and 80M/s for enterprise users, campus users and Internet cafe users in the flow table entries corresponding to the time period of 24: 00-8: 00.
Illustratively, the present embodiment provides a flow table structure of a network forwarding flow table as shown in table 2 below.
TABLE 2
| Period (time Period) | Matching Policy (Matching rules) | Action (Action to execute) |
| 8:00～18:00 | Match Policy 1 | Action 1 |
| 18:00～24:00 | Match Policy 2 | Action 2 |
| 24:00～8:00 | Match Policy 3 | Action 3 |
The exemplary flow table structure includes entries such as a time period, a matching rule, and an executed action, where the matching rule is specifically the flow table entry generated in the foregoing for each type of user in a corresponding time period, and the executed action may be, but is not limited to, various flow table actions defined in OpenFlow, such as forwarding, dropping, queuing, modifying a domain, and the like.
In the SDN network traffic optimization, the SDN controller may specifically perform statistics and analysis on traffic information collected and reported by the forwarding device through a statistics analysis and policy making module of the SDN controller, make a network forwarding traffic table based on a time period according to regularity information obtained through the analysis, and then call a flowwrite service of the SDN controller to issue the network forwarding traffic table based on the time period to the forwarding device through an Openflow plugin.
In practical implementation, the network forwarding flow table based on the time period may be issued by extending the reserved field of the OFPT _ F L OW _ MOD message in the openflow protocol, where, but not limited to, the start time of the time period may be stored in the first 16 bits of the 32-bit reserved in the protocol, and the end time of the time period may be stored in the last 16 bits.
And 204, matching corresponding network flow processing rules aiming at corresponding time for network users of corresponding types according to the network forwarding flow table.
On the basis of generating the corresponding relation between the time and the network flow for different types of network users in the first time period in a network forwarding flow table form, the corresponding network flow processing rule for the corresponding time can be matched for the corresponding type of network users according to the network forwarding flow table.
Taking the network forwarding flow table in table 2 as an example, in the time period of 8:00 to 18:00, since the matching rule is Policy1, the network traffic processing rules for three types of users, i.e. enterprise, campus, and internet cafe, in the time period are respectively: network traffic processing is carried out on the network users of enterprises, campuses and internet cafes on the basis of network bandwidths of 70M/s, 2M/s and 20M/s respectively.
Next, this step generates a corresponding network traffic processing instruction for a corresponding time for a corresponding type of network user according to the matched corresponding network traffic processing rule.
For example, for the network traffic processing rule matched for three types of users, namely, an enterprise, a campus and an internet cafe, in the time period of 8:00 to 18:00, a first network traffic processing instruction for the enterprise user may be generated in the time period, where the instruction is used to instruct the enterprise user to perform network traffic data processing based on a network bandwidth of 70M/s; correspondingly, a second network traffic processing instruction for the campus user can be generated in the time period, and the instruction is used for instructing network traffic data processing for the enterprise user based on the network bandwidth of 2M/s; third network traffic processing instructions for the internet cafe user may be generated for the time period, the instructions for instructing network traffic data processing for the enterprise user based on the network bandwidth of 20M/s.
Certainly, in practical application, the first, second, and third network traffic processing instructions may be specifically generated in the form of one instruction, that is, the generated one instruction is used to instruct, in a time period of 8:00 to 18:00, to perform network traffic data processing, such as forwarding, discarding network data, for the enterprise, campus, and internet cafe users based on network bandwidths of 70M/s, 2M/s, and 20M/s, respectively.
In specific implementation, a time judgment module may be added to judge a currently valid matching rule in the network forwarding flow table, and based on the currently valid matching rule, a network traffic processing instruction is generated, and network traffic data processing based on the instruction generation is performed, so as to implement network traffic optimization.
Still taking the flow optimization scenario of the SDN network as an example, after receiving the network forwarding flow table issued by the SDN controller, the forwarding device may determine, based on the time determination module, a matching rule that takes effect in the network forwarding flow table at the current time, specifically, for the network forwarding flow table of table 2, in 8: 00-18:00, the rule in effect is Policy1, so that network traffic data processing can be performed based on Policy1 (e.g., generating instructions and processing network traffic data of users based on the generated instructions); at 18: 00-24: 00, the rule in effect is Policy 2; and at 24: 00-8: 00, the rule in effect is Policy 3.
It should be noted that the generated network forwarding flow table corresponds to the first time period, so that, in the first time period, the network forwarding flow table can be used to perform time (time period) -based network traffic data processing on various types of network users. For example, taking the first time period of table 2 as 1 day as an example, the network traffic data of different types of users may be processed based on the corresponding matching rules of table 2 at different time periods of 1 day. In practical application, the network forwarding flow table can be updated by periodically or aperiodically re-collecting the newer network traffic information in the first time period.
The traffic optimization method provided by the embodiment of the application generates the corresponding relation between time and network traffic in a first time period based on historical network traffic information corresponding to different times in the first time period, generates a network traffic processing instruction based on the corresponding relation, and processes the network traffic data of a user based on the network traffic processing instruction on the basis. Therefore, by using the scheme of the application, the network flow data can be processed based on the pre-generated corresponding relation between the time and the network flow in the first time period, the collection and calculation of the flow information and the formulation and issuing of the flow table are not required to be carried out in real time, and the pressure of the network core equipment in the network flow optimization can be effectively relieved.
In another embodiment, the present application provides a traffic optimization device, which may be applied to a traffic optimization scenario of a network, such as specifically applied to a core device of an SDN network for network traffic optimization, and referring to a schematic structural diagram of a traffic optimization device shown in fig. 4, the device may include:
an obtaining unit 401, configured to obtain network traffic information in a first time period; wherein the network traffic information comprises: historical network traffic information corresponding to different times during the first time period.
In an actual traffic usage scenario, the usage of network traffic by users is often regular, for example, for enterprise users, the peak time of the usage of the network traffic is generally working time of working day (e.g., 8:00-12:00 and 12:00-18:00), and the non-working time of the non-working day and the working day is less usage of the network traffic.
Based on this, the application aims to analyze the usage rules of the user on the network traffic at different times in a certain time period through historical network traffic information when the user uses the network traffic at different times in the time period, and further perform time-based network traffic data processing on the user in the future time period based on the analysis of the usage rules, such as performing traffic data processing on the enterprise user based on a larger bandwidth in the working day and working time of the enterprise user.
The first time period may be a preset time period with a certain time length, such as but not limited to a day, two days, a week, a month, and so on.
The step of obtaining the network flow information in the first time period, namely obtaining the historical network flow information of the user corresponding to different times in the first time period, is realized to provide analysis basis for the usage rule of the network flow in the first time period.
Here, it should be noted that the network traffic information in the first time period obtained in this step is not limited to the network traffic information in only one first time period, for example, the first time period is 1 day, and the obtained network traffic information in the first time period is not limited to historical network traffic information in only different times in one day, but may be historical network traffic information in different times in multiple days by the user, more specifically, for example, historical network traffic information corresponding to different times of each day in the last 5 working days by the enterprise user, historical network traffic information corresponding to different times of each working day in each working day included in the last month, and the like, and the present application does not limit this.
A correspondence generating unit 402, configured to generate a correspondence between time in the first time period and network traffic based on the network traffic information in the first time period.
On the basis of obtaining the network flow information in the first time period, namely obtaining historical network flow information of the user corresponding to different times in the first time period, analyzing the usage rule of the user on the network flow at different times in the first time period by using the obtained data as a basis, and further generating the corresponding relation between the different times and the network flow in the first time period for the user according to the rule result obtained by analyzing so as to provide a control basis for the subsequent network flow optimization control in the first time period.
An instruction generating unit 403, configured to generate a network traffic processing instruction based on the correspondence.
Based on generating the correspondence between the time and the network traffic within the first time period for the user, a corresponding network traffic processing instruction may be generated based on the generated correspondence.
It should be noted that, since the correspondence is specifically a correspondence between time and network traffic, for example, an enterprise user corresponds to a network traffic with a higher bandwidth value during working time of a working day, and corresponds to a network traffic with a lower bandwidth value during non-working time, etc., a corresponding network traffic processing instruction generated according to the correspondence is also time-based, for example, a first network traffic processing instruction corresponding to a higher bandwidth value is generated for the enterprise user during working time, and a second network traffic processing instruction corresponding to a lower bandwidth value is generated during non-working time.
A processing unit 404, configured to process the network traffic data of the user based on the network traffic processing instruction.
Then, the network traffic data of the user may be processed according to the network traffic processing instruction, still taking the enterprise user as an example, during the working time of the working day, according to the first network traffic processing instruction, the required network traffic data processing may be performed for the enterprise user based on a higher network bandwidth, while during the non-working time, according to the second network traffic processing instruction, the required network traffic data processing may be performed for the enterprise user based on a lower network bandwidth.
According to the scheme, the traffic optimization device provided by the embodiment of the application generates the corresponding relation between the time and the network traffic in the first time period based on the historical network traffic information corresponding to different times in the first time period, generates the network traffic processing instruction based on the corresponding relation, and processes the network traffic data of the user according to the network traffic processing instruction on the basis. Therefore, by using the scheme of the application, the network flow data can be processed based on the pre-generated corresponding relation between the time and the network flow in the first time period, the collection and calculation of the flow information and the formulation and issuing of the flow table are not required to be carried out in real time, and the pressure of the network core equipment in the network flow optimization can be effectively relieved.
In the following embodiments of the present application, the obtaining unit is specifically configured to:
and obtaining historical network flow information corresponding to different types of network users at different times in a first time period.
Specifically, the usage rules of different types of users on the network are often different, for example, the peak time when an enterprise user uses the network traffic is generally the working time of a working day (e.g., 8:00-12: 001 and 3: 00-18:00), the remaining time uses the network traffic less, and the peak time when a campus user or a home user uses the network traffic is generally the evening (e.g., 18: 00-22: 00) and the weekend.
In order to implement network traffic optimization for different types of users, the embodiment first obtains historical network traffic information corresponding to different types of network users at different times in a first time period. For example, historical network traffic information corresponding to different types of network users in a first time period is obtained for enterprise users, campus users, home users, internet cafe users, and the like.
The first time period may be a preset time period with a certain time length, such as but not limited to a day, two days, a week, a month, and so on.
Here, it should be noted that the network traffic information in the first time period obtained in this step is not limited to the network traffic information in only one first time period, for example, the first time period is 1 day, and the obtained network traffic information in the first time period is not limited to historical network traffic information in only different times in one day, but may be historical network traffic information in different times in multiple days for corresponding types of users, more specifically, for example, historical network traffic information corresponding to different times of each working day of the last 5 working days for enterprise users, historical network traffic information corresponding to different times of each working day of the last month for campus users, and the like, and the present application does not limit this.
Taking SDN network traffic optimization as an example, referring to fig. 3, a schematic diagram of a principle for implementing SDN network traffic optimization by using the method of the present application is provided, where an SDN controller may formulate and issue a traffic collection task to a forwarding device through a network traffic collection module included in the SDN controller, and the formulated and issued traffic collection task includes collection content, a collection period, and the like. And a flow acquisition reporting module of the forwarding equipment acquires and reports flow information (reports the flow information to the SDN controller) based on an acquisition task issued by the SDN controller. In actual implementation, the collection task can be issued through the openflow protocol. It should be noted here that, since the collected traffic information is specifically used as an analysis basis for a usage rule of user network traffic, and further traffic optimization is achieved, so as to achieve optimization of current network traffic, the SDN network should complete a task of collecting the network traffic information in advance, for example, network traffic information collection of an enterprise user or a campus user may be performed a week in advance, so that historical data support is provided for current network traffic optimization through preprocessing work of data collection.
Correspondingly, the correspondence generating unit is specifically configured to: analyzing the use rules of the network traffic of the different types of network users at different times according to the historical network traffic information corresponding to the different types of network users at different times in the first time period; and generating the corresponding relation between the time and the network flow for the different types of network users in the first time period according to the use rules of the different types of network users on the network flow at different times.
After obtaining the historical network traffic information corresponding to different types of network users at different times in the first time period, for example, after obtaining the historical network traffic information corresponding to different types of users, such as enterprise users, campus users, and home users, at different times in the first time period, the historical network traffic information may be counted and analyzed to analyze the usage rules of the network traffic by the different types of network users at different times.
The usage rules analyzed typically include at least the bandwidth requirements of different types of network users for network traffic at different times. In a real application scenario, a fixed type of network user tends to have a relatively stable bandwidth requirement for a sustained period of time, and thus, more specifically, the usage rules may include bandwidth requirements of different types of network users for network traffic at different time periods.
Referring to table 1 below, table 1 exemplarily provides information on usage rules of network traffic for three different users, namely, an enterprise, a campus, and an internet cafe.
TABLE 1
As can be seen from the above Table 1, the peak time of the network traffic of the enterprise user in the 1 day time period (assumed to be working days) is 8: 00-18:00, and there exists a bandwidth demand of about 70M/S, the peak time of the network traffic of the campus user in the 1 day time period is 18: 00-24: 00, and there exists a bandwidth demand of about 90M/S, and the peak time of the network traffic of the Internet cafe user in the 1 day time period is 24: 00-8: 00, and the sub-peak time is 18: 00-24: 00, and there exist bandwidth demands of about 80M/S and 50M/S, respectively.
After analyzing the usage rules of different types of network users for network traffic at different times based on the historical network traffic information, the corresponding relationship between the time and the network traffic for the different types of network users in the first time period can be generated based on the usage rules obtained by the analysis.
In this embodiment, the correspondence between the time and the network traffic for the different types of network users in the first time period is generated in the form of a network forwarding flow table, specifically, in this embodiment, a network forwarding flow table based on time is generated according to bandwidth requirements of the different types of network users on the network traffic at different times; the network forwarding flow table at least comprises corresponding relations among different time, different types of network users and different network flow forwarding rules.
Taking the traffic usage rules of the three types of network users, i.e., enterprise, campus, and internet cafe, in table 1, for the time period of 8: 00-18:00, an entry of a network forwarding flow table mainly based on user a, i.e., an enterprise user, may be generated, and the entry is policy1, where in the entry corresponding to the time period of 8: 00-18:00, the enterprise user is configured with a bandwidth of about 70M/s, and the campus user and the internet cafe user are configured with bandwidths of about 2M/s and 20M/s, respectively. And generating a flow table entry Policy2 mainly aiming at the campus user in the time period of 18: 00-24: 00, and respectively configuring network bandwidths of about 2M/s, 90M/s and 50M/s for enterprise users, campus users and Internet cafe users in the entries corresponding to the time period of 18: 00-24: 00. And for the time period of 24: 00-8: 00, generating a flow table entry Policy3 mainly aiming at the Internet cafe users, and respectively configuring network bandwidths of about 0.5M/s, 1M/s and 80M/s for enterprise users, campus users and Internet cafe users in the flow table entries corresponding to the time period of 24: 00-8: 00.
Illustratively, the present embodiment provides a flow table structure of a network forwarding flow table as shown in table 2 below.
TABLE 2
| Period (time Period) | Matching Policy (Matching rules) | Action (Action to execute) |
| 8:00～18:00 | Match Policy 1 | Action 1 |
| 18:00～24:00 | Match Policy 2 | Action 2 |
| 24:00～8:00 | Match Policy 3 | Action 3 |
The exemplary flow table structure includes entries such as a time period, a matching rule, and an executed action, where the matching rule is specifically the flow table entry generated in the foregoing for each type of user in a corresponding time period, and the executed action may be, but is not limited to, various flow table actions defined in OpenFlow, such as forwarding, dropping, queuing, modifying a domain, and the like.
In the SDN network traffic optimization, the SDN controller may specifically perform statistics and analysis on traffic information collected and reported by the forwarding device through a statistics analysis and policy making module of the SDN controller, make a network forwarding traffic table based on a time period according to regularity information obtained through the analysis, and then call a flowwrite service of the SDN controller to issue the network forwarding traffic table based on the time period to the forwarding device through an Openflow plugin.
In practical implementation, the network forwarding flow table based on the time period may be issued by extending the reserved field of the OFPT _ F L OW _ MOD message in the openflow protocol, where, but not limited to, the start time of the time period may be stored in the first 16 bits of the 32-bit reserved in the protocol, and the end time of the time period may be stored in the last 16 bits.
On this basis, the instruction generation unit is specifically configured to: according to the network forwarding flow table, matching corresponding network flow processing rules aiming at corresponding time for network users of corresponding types; and generating a corresponding network flow processing instruction aiming at corresponding time for the corresponding type of network users according to the matched corresponding network flow processing rule.
On the basis of generating the corresponding relation between the time and the network flow for different types of network users in the first time period in a network forwarding flow table form, the corresponding network flow processing rule for the corresponding time can be matched for the corresponding type of network users according to the network forwarding flow table.
Taking the network forwarding flow table in table 2 as an example, in the time period of 8:00 to 18:00, since the matching rule is Policy1, the network traffic processing rules for three types of users, i.e. enterprise, campus, and internet cafe, in the time period are respectively: network traffic processing is carried out on the network users of enterprises, campuses and internet cafes on the basis of network bandwidths of 70M/s, 2M/s and 20M/s respectively.
Next, this step generates a corresponding network traffic processing instruction for a corresponding time for a corresponding type of network user according to the matched corresponding network traffic processing rule.
For example, for the network traffic processing rule matched for three types of users, namely, an enterprise, a campus and an internet cafe, in the time period of 8:00 to 18:00, a first network traffic processing instruction for the enterprise user may be generated in the time period, where the instruction is used to instruct the enterprise user to perform network traffic data processing based on a network bandwidth of 70M/s; correspondingly, a second network traffic processing instruction for the campus user can be generated in the time period, and the instruction is used for instructing network traffic data processing for the enterprise user based on the network bandwidth of 2M/s; third network traffic processing instructions for the internet cafe user may be generated for the time period, the instructions for instructing network traffic data processing for the enterprise user based on the network bandwidth of 20M/s.
Certainly, in practical application, the first, second, and third network traffic processing instructions may be specifically generated in the form of one instruction, that is, the generated one instruction is used to instruct, in a time period of 8:00 to 18:00, to perform network traffic data processing, such as forwarding, discarding network data, for the enterprise, campus, and internet cafe users based on network bandwidths of 70M/s, 2M/s, and 20M/s, respectively.
In specific implementation, a time judgment module may be added to judge a currently valid matching rule in the network forwarding flow table, and based on the currently valid matching rule, a network traffic processing instruction is generated, and network traffic data processing based on the instruction generation is performed, so as to implement network traffic optimization.
Still taking the flow optimization scenario of the SDN network as an example, after receiving the network forwarding flow table issued by the SDN controller, the forwarding device may determine, based on the time determination module, a matching rule that takes effect in the network forwarding flow table at the current time, specifically, for the network forwarding flow table of table 2, in 8: 00-18:00, the rule in effect is Policy1, so that network traffic data processing can be performed based on Policy1 (e.g., generating instructions and processing network traffic data of users based on the generated instructions); at 18: 00-24: 00, the rule in effect is Policy 2; and at 24: 00-8: 00, the rule in effect is Policy 3.
It should be noted that the generated network forwarding flow table corresponds to the first time period, so that, in the first time period, the network forwarding flow table can be used to perform time (time period) -based network traffic data processing on various types of network users. For example, taking the first time period of table 2 as 1 day as an example, the network traffic data of different types of users may be processed based on the corresponding matching rules of table 2 at different time periods of 1 day. In practical application, the network forwarding flow table can be updated by periodically or aperiodically re-collecting the newer network traffic information in the first time period.
The traffic optimization device provided by the embodiment of the application generates the corresponding relation between time and network traffic in a first time period based on historical network traffic information corresponding to different times in the first time period, generates a network traffic processing instruction based on the corresponding relation, and processes the network traffic data of a user based on the network traffic processing instruction on the basis. Therefore, by using the scheme of the application, the network flow data can be processed based on the pre-generated corresponding relation between the time and the network flow in the first time period, the collection and calculation of the flow information and the formulation and issuing of the flow table are not required to be carried out in real time, and the pressure of the network core equipment in the network flow optimization can be effectively relieved.
In summary, the method and the device have the advantages that the working pressure of network core devices (such as an SDN controller, a forwarding device and the like) in network traffic optimization can be greatly reduced, network fluctuation can be reduced and network stability can be improved due to the fact that the traffic processing rule conforming to the user traffic usage rule is formulated based on historical data analysis of network traffic, besides network traffic optimization, the technical concept of the method and the device can be applied to other time slot-based processing scenes, such as AC L (Access Control L ist) and other time slot-based forwarding strategy formulations, and time slot-based S L A (Service-L event agent) settings and the like based on time slot charging rules.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
For convenience of description, the above system or apparatus is described as being divided into various modules or units by function, respectively. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
Finally, it is further noted that, herein, relational terms such as first, second, third, fourth, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (6)
1. A method for traffic optimization, comprising:
obtaining network flow information in a first time period; wherein the network traffic information comprises: historical network traffic information corresponding to different times during the first time period; the obtaining network traffic information in the first time period includes: obtaining historical network flow information corresponding to different types of network users at different times in a first time period; wherein, the peak time rules of the different types of network users using the network traffic are different;
generating a corresponding relation between the time and the network flow in the first time period based on the network flow information in the first time period; generating a corresponding relation between time and network traffic in the first time period based on the network traffic information in the first time period, including: analyzing the use rules of the network traffic of the different types of network users at different times according to the historical network traffic information corresponding to the different types of network users at different times in the first time period; generating a corresponding relation between the time and the network flow for the different types of network users in the first time period according to the usage rules of the different types of network users on the network flow at different times; wherein the usage rule at least comprises the bandwidth requirements of the different types of network users on the network traffic at different times;
generating a network flow processing instruction based on the corresponding relation;
and processing the network traffic data of the user based on the network traffic processing instruction.
2. The method of claim 1, wherein the usage pattern of the network traffic by the network user at different times at least comprises: network users demand bandwidth of network traffic at different times;
generating a corresponding relationship between the time and the network traffic for the different types of network users in the first time period according to the usage rules of the different types of network users for the network traffic at different times, including:
generating a network forwarding flow table based on time according to the bandwidth requirements of different types of network users on network flow at different times; the network forwarding flow table at least comprises corresponding relations among different time, different types of network users and different network flow forwarding rules.
3. The method of claim 2, wherein generating network traffic processing instructions based on the correspondence comprises:
according to the network forwarding flow table, matching corresponding network flow processing rules aiming at corresponding time for network users of corresponding types;
and generating a corresponding network flow processing instruction aiming at corresponding time for the corresponding type of network users according to the matched corresponding network flow processing rule.
4. A flow optimization device, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring network flow information in a first time period; wherein the network traffic information comprises: historical network traffic information corresponding to different times during the first time period; the obtaining unit is specifically configured to: obtaining historical network flow information corresponding to different types of network users at different times in a first time period; wherein, the peak time rules of the different types of network users using the network traffic are different;
a correspondence generating unit, configured to generate a correspondence between time and network traffic in the first time period based on the network traffic information in the first time period; the correspondence generating unit is specifically configured to: analyzing the use rules of the network traffic of the different types of network users at different times according to the historical network traffic information corresponding to the different types of network users at different times in the first time period; generating a corresponding relation between the time and the network flow for the different types of network users in the first time period according to the usage rules of the different types of network users on the network flow at different times; wherein the usage rule at least comprises the bandwidth requirements of the different types of network users on the network traffic at different times;
the instruction generating unit is used for generating a network flow processing instruction based on the corresponding relation;
and the processing unit is used for processing the network flow data of the user based on the network flow processing instruction.
5. The apparatus of claim 4, wherein the usage pattern of the network traffic by the network user at different times at least comprises:
network users demand bandwidth of network traffic at different times;
the corresponding relationship generating unit generates, according to usage rules of network traffic by different types of network users at different times, a corresponding relationship between time and network traffic for the different types of network users in the first time period, and specifically includes:
generating a network forwarding flow table based on time according to the bandwidth requirements of different types of network users on network flow at different times; the network forwarding flow table at least comprises corresponding relations among different time, different types of network users and different network flow forwarding rules.
6. The apparatus according to claim 5, wherein the instruction generation unit is specifically configured to:
according to the network forwarding flow table, matching corresponding network flow processing rules aiming at corresponding time for network users of corresponding types; and generating a corresponding network flow processing instruction aiming at corresponding time for the corresponding type of network users according to the matched corresponding network flow processing rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710527008.7A CN107248959B (en) | 2017-06-30 | 2017-06-30 | Flow optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710527008.7A CN107248959B (en) | 2017-06-30 | 2017-06-30 | Flow optimization method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107248959A CN107248959A (en) | 2017-10-13 |
| CN107248959B true CN107248959B (en) | 2020-07-24 |
Family
ID=60013690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710527008.7A Active CN107248959B (en) | 2017-06-30 | 2017-06-30 | Flow optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107248959B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111292523B (en) * | 2018-12-06 | 2023-04-07 | 中国信息通信科技集团有限公司 | Network intelligent system |
| CN110380892A (en) * | 2019-06-17 | 2019-10-25 | 江门职业技术学院 | A kind of classroom band width control method, device, equipment and storage medium |
| CN111756646B (en) * | 2020-07-08 | 2023-09-29 | 腾讯科技（深圳）有限公司 | Network transmission control method, device, computer equipment and storage medium |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7841002B2 (en) * | 2001-12-06 | 2010-11-23 | Ectel Ltd. | Method for detecting a behavior of interest in telecommunication networks |
| US9264321B2 (en) * | 2009-12-23 | 2016-02-16 | Juniper Networks, Inc. | Methods and apparatus for tracking data flow based on flow state values |
| CN102088754B (en) * | 2010-12-06 | 2013-11-13 | 中国人民解放军信息工程大学 | Network access behavior-based access control method and system for wireless local area network |
| JP2016508353A (en) * | 2013-01-10 | 2016-03-17 | ネットフロー ロジック コーポレーション | Improved streaming method and system for processing network metadata |
| CN105101302B (en) * | 2014-04-30 | 2019-03-08 | 宇龙计算机通信科技(深圳)有限公司 | Flow managing method and system based on user's use habit |
| WO2016086406A1 (en) * | 2014-12-05 | 2016-06-09 | 华为技术有限公司 | Network resource deployment method and device |
| US10536357B2 (en) * | 2015-06-05 | 2020-01-14 | Cisco Technology, Inc. | Late data detection in data center |
| CN105227489B (en) * | 2015-08-26 | 2019-05-31 | 联想(北京)有限公司 | A kind of bandwidth management method and electronic equipment |
| CN105471759B (en) * | 2016-01-11 | 2018-06-01 | 北京百度网讯科技有限公司 | The network traffics dispatching method and device of data center |
| CN105791157B (en) * | 2016-04-20 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of distribution method of flow, distribution system and server |
| CN106060849B (en) * | 2016-05-26 | 2019-08-20 | 重庆大学 | A kind of network formats optimizing distribution method in heterogeneous network |
| CN106357559B (en) * | 2016-09-21 | 2020-02-21 | 东软集团股份有限公司 | Bandwidth allocation method and device |
| CN106411766A (en) * | 2016-09-30 | 2017-02-15 | 赛特斯信息科技股份有限公司 | Flow scheduling system and method based on SDN |
-
2017
- 2017-06-30 CN CN201710527008.7A patent/CN107248959B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107248959A (en) | 2017-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | QoE-driven power scheduling in smart grid: architecture, strategy, and methodology | |
| CN107248959B (en) | Flow optimization method and device | |
| CN102594675B (en) | Traffic control system and method | |
| JP2017126975A (en) | Network traffic scheduling method and device of data center | |
| CN106899857B (en) | Server load adjusting method, device and server | |
| CN108924221A (en) | The method and apparatus for distributing resource | |
| CN100459589C (en) | A method to monitor flow and flow monitoring equipment | |
| CN104753732A (en) | Distribution based network traffic analysis system and method | |
| CN105227429B (en) | A kind of information-pushing method and device | |
| Jun et al. | Mining and modelling the dynamic patterns of service providers in cellular data network based on big data analysis | |
| CN107171839A (en) | A kind of bandwidth traffic cost control method | |
| CN107820281A (en) | A kind of method and router for distributing Internet resources | |
| Yu et al. | Spectrum investment with uncertainty based on prospect theory | |
| CN110839069B (en) | Node data deployment method, node data deployment system and medium | |
| DE10297645T5 (en) | Method and device for load sharing and data distribution in servers | |
| CN112367276A (en) | Network resource dynamic self-adaption method and system based on network flow priority | |
| Dabeer et al. | Timing tweets to increase effectiveness of information campaigns | |
| Do et al. | A new finite-source queueing model for mobile cellular networks applying spectrum renting | |
| CN103281355A (en) | Fuzzy decision-based server push method | |
| CN103093377A (en) | Method and system of advertisement putting | |
| CN104871499B (en) | Communication node, control device and the management method for controlling data entries | |
| Qian et al. | The role of damping and low pass filtering in the stability of discrete time implemented robot force control | |
| Zseby et al. | Packet sampling for flow accounting: Challenges and limitations | |
| CN107070700A (en) | A kind of network service provider method of identity-based automatic identification | |
| US20200314019A1 (en) | Managing bandwidth based on user behavior |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |