CN103685072A - Method for quickly distributing network flow - Google Patents
Method for quickly distributing network flow Download PDFInfo
- Publication number
- CN103685072A CN103685072A CN201310608951.2A CN201310608951A CN103685072A CN 103685072 A CN103685072 A CN 103685072A CN 201310608951 A CN201310608951 A CN 201310608951A CN 103685072 A CN103685072 A CN 103685072A
- Authority
- CN
- China
- Prior art keywords
- network traffics
- key
- network
- business
- interval
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention relates to the technical field of distribution of network resources, and discloses a method for quickly distributing network flow. The method comprises the following steps of monitoring an occupation rule of a key business of a key user on the network flow in real time by using a network flow monitoring module; predicting the network flow of the key business of the key user in a next time quantum according to a historical rule; researching corresponding bandwidth and corresponding duration in the network flow to transmit the key business of the key user; and transmitting a business request by using the reserved network flow when the key business of the key user initiates the business request. The network flow of the key business of the key user in the next time quantum is predicted by the historical occupation rule of the key business of the key user on the network flow; the corresponding bandwidth and the corresponding duration are reserved to transmit the key business of the key user; and transmission of the key business is guaranteed.
Description
Technical field
The present invention relates to Resource Allocation in Networks technical field, relate in particular to a kind of method of network traffics fast allocation.
Background technology
Internet network is a multiplexed network, and network traffics have burst characteristic clearly, easily causes within a certain period of time network congestion, and network traffics distribute to be exactly in order to solve when the network congestion service quality end to end.
Prior art one, application number is CN201210471234.5, open day is on November 20th, 2012, name is called " system of smart allocation WLAN user network bandwidth ", and the system that it discloses a kind of smart allocation WLAN user network bandwidth comprises the system server that produces the instruction of the mean allocation network bandwidth according to number of users, be called for short system server, controller, WAP (wireless access point) and user side, described user side, WAP (wireless access point), controller and system server are electrically connected to successively.By system server being set according to user's quantity, by controller, the network of access WAP (wireless access point) is carried out to intelligent reasonable distribution, well solved that the bandwidth that the access user that exists in prior art uses is fixed, the undue residue of the network bandwidth causes the problems such as waste or network bandwidth wretched insufficiency cause normally surfing the Net, reached according to the object of number of users reasonable distribution network.Its shortcoming is that the method for the mean allocation network bandwidth is subject to cannot guarantee key user's network demand in limited time at Internet resources.
Prior art two, application number is " CN201110256618.0 ", open day is on 01 11st, 2012, name is called " method and the device that in a kind of EVDO system, guarantee applied business QoS ", a kind of method that guarantees applied business QoS in EVDO system is wherein disclosed, comprise the steps: the message on main connection single current to detect and add up, identify the current main applied business type of user; According to the QoS demand of described current main applied business type, carry out the Resource Allocation in Networks of wireless side; For described current main applied business type, when the integrated flow of its distribution or Mean Speed are surpassed to default threshold value, the Internet resources of distribution are discharged.Adopt the inventive method, can provide QoS to guarantee for the applied business that difference is transmitted demand, thereby greatly improve user's experience, also can make the system resource of whole network be used adequately reasonably simultaneously.The invention also discloses the device that guarantees applied business QoS in a kind of EVDO system, comprise that main business type identification module, resource distribution module and protection recover module.The business that method for allocating network flow based on QoS can be protected key user obtains enough network traffics, but when network traffics are blocked up, needs first by key user, to propose flow application, and then releasing network flow just can distribute, and has affected dispensing rate.
Prior art three, application number is " CN200610165423.4 ", open day is on 06 25th, 2008, and name is called " resource management system in a kind of mobile communications network and method ", and it discloses resource management system and method in a kind of mobile communications network.This system comprises terminal and network equipment, and network equipment comprises the reserved bandwidth unit of distributing, for according to reserved service bandwidth parameter and the network side available bandwidth of terminal, for described terminal is carried out resource reservation and allocated bandwidth; Flow controlling unit, for according to sending to the data of terminal, and the channel parameter of terminal, terminal is carried out to the possibility of high speed descending sharing channel change and predict, produce Flow Control capability distribution frame, carry out flow control; Packet scheduling and resource allocation unit, distribute for carrying out packet scheduling and resource.It makes high speed downlink packet access can support preferably various types of business and can make full use of Internet resources.Adopt the mode of resource reservation can meet key user's business demand, but when key user and business are inactive, can cause the waste of Internet resources.
Summary of the invention
For method for allocating network flow of the prior art, can not be key user all rationally carry out the technical problem of assignment of traffic in active and inactive two kinds of situations of key user, a kind of method of network traffics fast allocation is provided.
The invention discloses a kind of method of network traffics fast allocation, the take rule of the key business that the steps include: Network Traffic Monitoring module Real-Time Monitoring key user to network traffics, according to historical law, dope the network traffics of key user's key business in the next time period, then in network traffics, reserve corresponding bandwidth and duration for transmitting key user's key business, when key user's key business initiating business request, adopt reserved network traffics to transmit.
Further, said method specifically comprises the following steps: step 1, all users' of Network Traffic Monitoring module Real-Time Monitoring network traffics, extracts the take rule of key user's key business to network traffics; Step 2, all users' of obtaining according to step 1 network traffics rule, according to the network traffics of all users in the next time period of historical law prediction, when the network traffics of prediction higher than set threshold value time, enter step 3, otherwise continue execution step one and step 2; The take rule of step 3, the key user's that obtains according to step 1 key business to network traffics, dope the network traffics of key user's key business in the next time period, and in network traffics, reserve corresponding bandwidth and duration for transmitting key user's key business.
Further, the above-mentioned method according to historical law prediction network traffics is specially Prediction of Markov method.
Further, the above-mentioned method according to historical law prediction network traffics specifically comprises the following steps: that (1) analyze the network traffics of actual measurement, get N group web-based history flow, each group all comprises the web-based history flow L (T) of current time t and the web-based history flow L (T+1) of next moment T+1; (2) L (T) and L (T+1) are divided into respectively to a plurality of network traffics interval, judge that current actual measurement network traffics L (t) corresponds to the network traffics interval of L (T), according to the web-based history flow L (T) in interval, the network traffics that obtain corresponding L (T+1) are interval; (3) in the network traffics interval of the L selecting (T+1), find and comprise L (T+1) to be worth maximum network traffics interval, interval using it as predicted flow rate; (4) according to predicted flow rate interval, obtain predicted flow rate.
Further, above-mentionedly according to predicted flow rate interval, obtain predicted flow rate and be specially: the maximum in predicted flow rate interval is as predicted flow rate; Or in predicted flow rate interval, the maximum of historical data is as predicted flow rate; The mean value of historical data is as predicted flow rate again or in predicted flow rate interval.
Further, the above-mentioned method according to historical law prediction network traffics is specially artificial neural network learning method.
Further, the above-mentioned method according to historical law prediction network traffics is specially: first by Prediction of Markov method, obtain predicted state, sending into artificial neural net learns again, artificial neural net carries out matching according to predicted state to network traffics, thereby provides the network traffics of prediction.
By adopting above technical scheme, beneficial effect of the present invention is: the mode by intelligent predicting has realized dynamically reserved to Internet resources, and reserving network resources, realizes Internet resources fast allocation and efficient utilization more accurately.Especially for key user and key business, when being subject to can greatly reduce by operation system, Internet resources carry out the response time delay that resource re-allocation is brought in limited time.Can learn according to the variation of network, user and service feature simultaneously, when user behavior custom or service resources occupancy mode change, can adjust automatically.The present invention is based on intelligent service resources fast distribution method, by adopting intelligentized means, without the response speed that has effectively improved traffic resource assignment, also effectively raise the utilance of Internet resources, and emphasis is guaranteed the resource requirement of key user and key business.
Accompanying drawing explanation
Fig. 1 is the flow chart of the method for network traffics fast allocation.
Fig. 2 is the flow chart of the method for predicting network flow.
Embodiment
Below in conjunction with Figure of description, describe the specific embodiment of the present invention in detail.
The invention discloses a kind of method of network traffics fast allocation, the take rule of the key business that the steps include: Network Traffic Monitoring module Real-Time Monitoring key user to network traffics, according to historical law, dope the network traffics of key user's key business in the next time period, then in network traffics, reserve corresponding bandwidth and duration for transmitting key user's key business, when key user's key business initiating business request, adopt reserved network traffics to transmit.The take network traffics that law forecasting go out later key user's key business of key business by historical key user to network traffics, and reserve corresponding bandwidth and duration for transmitting key user's key business, guaranteed the transmission of key business.
The flow chart of the method for network traffics fast allocation as shown in Figure 1, the present invention specifically comprises the following steps: step 1, all users' of Network Traffic Monitoring module Real-Time Monitoring network traffics, extracts the take rule of key user's key business to network traffics; Wherein key user and key user's key business can be determined according to Qos strategy, and key user's key business type can the type according to key user be set when key user networks, and also can set flexibly according to user's needs.Step 2, all users' of obtaining according to step 1 network traffics rule, according to the network traffics of all users in the next time period of historical law prediction, when the network traffics of prediction higher than set threshold value time, enter step 3, otherwise continue execution step one and step 2.The take rule of step 3, the key user's that obtains according to step 1 key business to network traffics, dope the network traffics of key user's key business in the next time period, and in network traffics, reserve corresponding bandwidth and duration for transmitting key user's key business.By the rule that takies of current and historical network traffics, dope the situation that overall network condition in the next time period and critical business take flow, when predicting may there is network congestion in the next time period time, reserving enough network bandwidths uses to key business, guaranteed the transmission quality of key business when network congestion, simultaneously when networking situation is smooth and easy, take less or do not take the reserved resource of network traffics, further having avoided the waste of Internet resources.Meanwhile, in the time of only may there is network congestion within the next time period, just carry out resource reservation processing, guaranteed the efficiency of the inventive method.
Further, the above-mentioned method according to historical law prediction network traffics is specially Prediction of Markov method.Adopt Markov switching matrix method, use transition probability matrix to analyze the variation tendency of network traffics.Markov is the mathematician of Russia, and he found in 20 beginnings of the century: some factor of a system is in transfer, and the n time result is affected by the result of n-1 only, only relevant with current status, irrelevant with other.Therefore by Prediction of Markov method, can go out according to current predicting network flow next network traffics constantly, Prediction of Markov method has successfully been used in the load prediction of electric power system at present, such as publication number is CN102426674A, open day is on 04 25th, 2012, name is called a kind of based on markovian Load Prediction In Power Systems method, so this patent is no longer described in detail method and the principle of Prediction of Markov method.
Further, the above-mentioned method according to historical law prediction network traffics can also adopt following step: (1) is analyzed the network traffics of actual measurement, get N group web-based history flow, each group all comprises the web-based history flow L (T) of current time t and the web-based history flow L (T+1) of next moment T+1; (2) L (T) and L (T+1) are divided into respectively to a plurality of network traffics interval, judge that the network traffics that current actual measurement network traffics L (t) is corresponding are interval, according to the web-based history flow L (T) in interval, the network traffics that obtain corresponding L (T+1) are interval; (3) in the network traffics interval of the L selecting (T+1), find and comprise L (T+1) to be worth maximum network traffics interval, interval using it as predicted flow rate; (4) according to predicted flow rate interval, obtain predicted flow rate.
Such as, current time t is on 01 01st, 2013 upper 10: 10: 10, when Dang Yitianwei unit divides, before on 01 01st, 2013, be all T the 10: 10: 10 all mornings, and according to the division of the time period of prediction, if within every 5 seconds, complete once prediction, above-mentioned (T+1) is 10: 10: 15 morning.When N is 5, collect 5 groups of web-based history flows, each group all comprises T constantly and (T+1) network traffics constantly, and T constantly and (T+1) 5 group network flows constantly comprises respectively (3.2,8.8), (2.6,7), (5.1,9), (3,6) and when (4,2), network traffics be take and 2 divided as unit; Five intervals of L (T) and L (T+1) are respectively 0-2,2-4,4-6,6-8,8-10.First and second, the L (T) of four, five groups is in second interval scope, the L (T) of the 3rd group is in the 3rd interval scope, the L of first and third group (T+1) is in the 5th interval scope, the second, the L of four groups (T+1) is in the 4th interval scope, and the L (T+1) of the 5th group is in first interval scope.When L (t) being detected and be 3, its scope falls between second network area of L (T), the value of the L (T+1) that in finding between second network area, L (T) is corresponding, be first and second, four, five groups of data, it is respectively 8.8,7,6 and 2, it belongs to respectively two three different intervals, and wherein 6 and 7 belong to 6-8 between same network area, and 6-8 is that predicted flow rate is interval.Find behind predicted flow rate interval, can set the maximum in predicted flow rate interval as predicted flow rate, such as 8; Also the maximum that can set historical data in predicted flow rate interval is as predicted flow rate, such as 7; Can also set the mean value of historical data in predicted flow rate interval as predicted flow rate, such as 6.5, etc. like that.
Further, the above-mentioned method according to historical law prediction network traffics can also be artificial neural net learning method.By artificial neural net, historical data is learnt, thereby obtained prediction data.
Further, the above-mentioned method according to historical law prediction network traffics can also be for first obtaining predicted state by Prediction of Markov method, sending into artificial neural net learns again, artificial neural net carries out matching according to predicted state to network traffics, thereby provides the network traffics of prediction.Resource reservation module main realized the reserved of Internet resources, and its operation principle as shown in Figure 2.Traffic separator is shunted the flow observing in network system according to the user of operation system and business information, chooses the flow that needs analysis.By high pass and two filters of low pass, extract respectively the high and low frequency traffic characteristic in network.After filtering, while choosing, sky, week, month component, according to each component value, be divided into 8 kinds of states, form the state components of 4 dimensions.Input using state component as Markovian decision is analyzed, and Markovian decision submodule is according to state transition probability, from current state, infers next state constantly, and will predict the outcome and give artificial neural net.Artificial neural net carries out matching according to predicted state to flow, provides predicted flow rate.Artificial neural net is learnt according to feedback information simultaneously, and the weight of each connection in network is adjusted.
After operation system initiating business request, resource distribution module is by according to the user in operation system and service priority information, and the bandwidth information of current network is carried out resource distribution.A business application has User Priority and two attributes of service priority simultaneously, when operation system, initiates request, and the distribution priority orders of resource is distributed according to comprehensive priority.Comprehensive priority numeral is less, and priority is higher.When the comprehensive priority of two applications is identical, by the sequencing of application time, distribute.
Given coefficient and parameter in the above embodiments; be to provide to those skilled in the art and realize or use invention; invention does not limit only gets aforementioned disclosed numerical value; in the situation that do not depart from the thought of invention; those skilled in the art can make various modifications or adjustment to above-described embodiment; thereby the protection range of invention do not limit by above-described embodiment, and it should be the maximum magnitude that meets the inventive features that claims mention.
Claims (7)
1. the method for a network traffics fast allocation, the take rule of the key business that the steps include: Network Traffic Monitoring module Real-Time Monitoring key user to network traffics, according to historical law, dope the network traffics of key user's key business in the next time period, then in network traffics, reserve corresponding bandwidth and duration for transmitting key user's key business, when key user's key business initiating business request, adopt reserved network traffics to transmit.
2. the method for network traffics fast allocation as claimed in claim 1, it is characterized in that described method specifically comprises the following steps: step 1, all users' of Network Traffic Monitoring module Real-Time Monitoring network traffics, extract the take rule of key user's key business to network traffics; Step 2, all users' of obtaining according to step 1 network traffics rule, according to the network traffics of all users in the next time period of historical law prediction, when the network traffics of prediction higher than set threshold value time, enter step 3, otherwise continue execution step one and step 2; The take rule of step 3, the key user's that obtains according to step 1 key business to network traffics, dope the network traffics of key user's key business in the next time period, and in network traffics, reserve corresponding bandwidth and duration for transmitting key user's key business.
3. the method for network traffics fast allocation as claimed in claim 2, is characterized in that the described method according to historical law prediction network traffics is specially Prediction of Markov method.
4. the method for network traffics fast allocation as claimed in claim 2, it is characterized in that the described method according to historical law prediction network traffics specifically comprises the following steps: that (1) analyze the network traffics of actual measurement, get N group web-based history flow, each group all comprises the web-based history flow L (T) of current time t and the web-based history flow L (T+1) of next moment T+1; (2) L (T) and L (T+1) are divided into respectively to a plurality of network traffics interval, judge that current actual measurement network traffics L (t) corresponds to the network traffics interval of L (T), according to the web-based history flow L (T) in interval, the network traffics that obtain corresponding L (T+1) are interval; (3) in the network traffics interval of the L selecting (T+1), find and comprise L (T+1) to be worth maximum network traffics interval, interval using it as predicted flow rate; (4) according to predicted flow rate interval, obtain predicted flow rate.
5. the method for network traffics fast allocation as claimed in claim 4, it is characterized in that describedly according to predicted flow rate interval, obtaining predicted flow rate and being specially: the maximum in predicted flow rate interval is as predicted flow rate, or in predicted flow rate interval the maximum of historical data is as predicted flow rate, then or predicted flow rate interval in the mean value of historical data as predicted flow rate.
6. the method for network traffics fast allocation as claimed in claim 2, is characterized in that the described method according to historical law prediction network traffics is specially artificial neural network learning method.
7. the method for network traffics fast allocation as claimed in claim 2, it is characterized in that the described method according to historical law prediction network traffics is specially: first by Prediction of Markov method, obtain predicted state, sending into artificial neural net learns again, artificial neural net carries out matching according to predicted state to network traffics, thereby provides the network traffics of prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310608951.2A CN103685072B (en) | 2013-11-27 | 2013-11-27 | A kind of method that network traffics are quickly distributed |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310608951.2A CN103685072B (en) | 2013-11-27 | 2013-11-27 | A kind of method that network traffics are quickly distributed |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103685072A true CN103685072A (en) | 2014-03-26 |
| CN103685072B CN103685072B (en) | 2016-11-02 |
Family
ID=50321426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310608951.2A Active CN103685072B (en) | 2013-11-27 | 2013-11-27 | A kind of method that network traffics are quickly distributed |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103685072B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346655A (en) * | 2014-10-08 | 2015-02-11 | 石家庄科林电气股份有限公司 | Application method of honeycomb structure dynamic algorithm to intelligent power utilization information management system |
| CN104468411A (en) * | 2014-11-28 | 2015-03-25 | 东莞宇龙通信科技有限公司 | Bandwidth allocation method and device and router |
| CN105791157A (en) * | 2016-04-20 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Flow distribution method, distribution system and server |
| CN105991362A (en) * | 2015-02-12 | 2016-10-05 | 腾讯科技（深圳）有限公司 | Method and device for setting fluctuation threshold range of data traffic |
| CN106533705A (en) * | 2015-09-15 | 2017-03-22 | 中国移动通信集团公司 | Data service flow quota allocation method and data service flow quota allocation device |
| CN106600042A (en) * | 2016-12-05 | 2017-04-26 | 武汉大学 | Mobile phone user networking period prediction method |
| CN106648906A (en) * | 2017-01-16 | 2017-05-10 | 杭州星数科技有限公司 | Container cloud resource intelligent recovery and enabling system and method |
| CN106685515A (en) * | 2017-01-05 | 2017-05-17 | 清华大学 | Allocation method and device for satellite resources in space information network |
| CN106817313A (en) * | 2015-12-01 | 2017-06-09 | 北京慧点科技有限公司 | A kind of method that network traffics are quickly distributed |
| CN107786454A (en) * | 2016-08-24 | 2018-03-09 | 中国电信股份有限公司 | Method and apparatus for network traffics scheduling |
| CN107959640A (en) * | 2016-10-14 | 2018-04-24 | 腾讯科技（深圳）有限公司 | Network dispatching method and device |
| CN108259376A (en) * | 2018-04-24 | 2018-07-06 | 北京奇艺世纪科技有限公司 | The control method and relevant device of server cluster service traffics |
| CN111565323A (en) * | 2020-03-23 | 2020-08-21 | 视联动力信息技术股份有限公司 | Flow control method and device, electronic equipment and storage medium |
| CN111970206A (en) * | 2020-08-21 | 2020-11-20 | 北京浪潮数据技术有限公司 | FC network flow control method, device and related components |
| CN112215667A (en) * | 2020-11-18 | 2021-01-12 | 中国联合网络通信集团有限公司 | User behavior prediction method and device |
| CN113098710A (en) * | 2021-03-26 | 2021-07-09 | 北京赛博云睿智能科技有限公司 | Network resource operation parameter self-adjusting and optimizing method and device |
| CN113824733A (en) * | 2021-10-16 | 2021-12-21 | 西安明德理工学院 | Computer network management system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1533193A (en) * | 2003-03-24 | 2004-09-29 | 华为技术有限公司 | Load control method of communication system and communicaton system and overload alarm device |
| CN101207895A (en) * | 2006-12-20 | 2008-06-25 | 中兴通讯股份有限公司 | System and method for managing resource in mobile communication network |
| CN101316141A (en) * | 2007-05-29 | 2008-12-03 | 华为技术有限公司 | Band width distribution method, device, communication apparatus and system |
| CN101466124A (en) * | 2007-12-19 | 2009-06-24 | 中国移动通信集团公司 | Control method and system for network bandwidth |
| CN101651568A (en) * | 2009-07-01 | 2010-02-17 | 青岛农业大学 | Method for predicting network flow and detecting abnormality |
| CN102204319A (en) * | 2011-04-28 | 2011-09-28 | 华为技术有限公司 | Method and device for artificial synthesis of network flow |
| CN102970691A (en) * | 2012-11-26 | 2013-03-13 | 中国联合网络通信集团有限公司 | Indoor and outdoor joint resource management method and base station |
| CN103379042A (en) * | 2012-04-25 | 2013-10-30 | 丛林网络公司 | Path weighted equal-cost multipath |
-
2013
- 2013-11-27 CN CN201310608951.2A patent/CN103685072B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1533193A (en) * | 2003-03-24 | 2004-09-29 | 华为技术有限公司 | Load control method of communication system and communicaton system and overload alarm device |
| CN101207895A (en) * | 2006-12-20 | 2008-06-25 | 中兴通讯股份有限公司 | System and method for managing resource in mobile communication network |
| CN101316141A (en) * | 2007-05-29 | 2008-12-03 | 华为技术有限公司 | Band width distribution method, device, communication apparatus and system |
| CN101466124A (en) * | 2007-12-19 | 2009-06-24 | 中国移动通信集团公司 | Control method and system for network bandwidth |
| CN101651568A (en) * | 2009-07-01 | 2010-02-17 | 青岛农业大学 | Method for predicting network flow and detecting abnormality |
| CN102204319A (en) * | 2011-04-28 | 2011-09-28 | 华为技术有限公司 | Method and device for artificial synthesis of network flow |
| CN103379042A (en) * | 2012-04-25 | 2013-10-30 | 丛林网络公司 | Path weighted equal-cost multipath |
| CN102970691A (en) * | 2012-11-26 | 2013-03-13 | 中国联合网络通信集团有限公司 | Indoor and outdoor joint resource management method and base station |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346655B (en) * | 2014-10-08 | 2017-04-12 | 石家庄科林电气股份有限公司 | Application method of honeycomb structure dynamic algorithm to intelligent power utilization information management system |
| CN104346655A (en) * | 2014-10-08 | 2015-02-11 | 石家庄科林电气股份有限公司 | Application method of honeycomb structure dynamic algorithm to intelligent power utilization information management system |
| CN104468411A (en) * | 2014-11-28 | 2015-03-25 | 东莞宇龙通信科技有限公司 | Bandwidth allocation method and device and router |
| CN105991362B (en) * | 2015-02-12 | 2019-10-29 | 腾讯科技（深圳）有限公司 | The fluctuation threshold range setting method and device of data traffic |
| CN105991362A (en) * | 2015-02-12 | 2016-10-05 | 腾讯科技（深圳）有限公司 | Method and device for setting fluctuation threshold range of data traffic |
| CN106533705A (en) * | 2015-09-15 | 2017-03-22 | 中国移动通信集团公司 | Data service flow quota allocation method and data service flow quota allocation device |
| CN106817313A (en) * | 2015-12-01 | 2017-06-09 | 北京慧点科技有限公司 | A kind of method that network traffics are quickly distributed |
| CN105791157A (en) * | 2016-04-20 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Flow distribution method, distribution system and server |
| CN107786454A (en) * | 2016-08-24 | 2018-03-09 | 中国电信股份有限公司 | Method and apparatus for network traffics scheduling |
| CN107786454B (en) * | 2016-08-24 | 2020-04-07 | 中国电信股份有限公司 | Method and apparatus for network traffic scheduling |
| CN107959640A (en) * | 2016-10-14 | 2018-04-24 | 腾讯科技（深圳）有限公司 | Network dispatching method and device |
| US10924356B2 (en) | 2016-10-14 | 2021-02-16 | Tencent Technology (Shenzhen) Company Limited | Network service scheduling method and apparatus, storage medium, and program product |
| CN107959640B (en) * | 2016-10-14 | 2020-07-07 | 腾讯科技（深圳）有限公司 | Network service scheduling method and device |
| CN106600042A (en) * | 2016-12-05 | 2017-04-26 | 武汉大学 | Mobile phone user networking period prediction method |
| CN106685515A (en) * | 2017-01-05 | 2017-05-17 | 清华大学 | Allocation method and device for satellite resources in space information network |
| CN106685515B (en) * | 2017-01-05 | 2019-10-22 | 清华大学 | The distribution method and device of Information Network Satellite resource |
| CN106648906A (en) * | 2017-01-16 | 2017-05-10 | 杭州星数科技有限公司 | Container cloud resource intelligent recovery and enabling system and method |
| CN108259376A (en) * | 2018-04-24 | 2018-07-06 | 北京奇艺世纪科技有限公司 | The control method and relevant device of server cluster service traffics |
| CN111565323A (en) * | 2020-03-23 | 2020-08-21 | 视联动力信息技术股份有限公司 | Flow control method and device, electronic equipment and storage medium |
| CN111970206A (en) * | 2020-08-21 | 2020-11-20 | 北京浪潮数据技术有限公司 | FC network flow control method, device and related components |
| CN112215667A (en) * | 2020-11-18 | 2021-01-12 | 中国联合网络通信集团有限公司 | User behavior prediction method and device |
| CN112215667B (en) * | 2020-11-18 | 2023-07-18 | 中国联合网络通信集团有限公司 | User behavior prediction method and device |
| CN113098710A (en) * | 2021-03-26 | 2021-07-09 | 北京赛博云睿智能科技有限公司 | Network resource operation parameter self-adjusting and optimizing method and device |
| CN113824733A (en) * | 2021-10-16 | 2021-12-21 | 西安明德理工学院 | Computer network management system |
| CN113824733B (en) * | 2021-10-16 | 2023-08-18 | 西安明德理工学院 | Computer network management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103685072B (en) | 2016-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103685072B (en) | A kind of method that network traffics are quickly distributed | |
| CN106817313A (en) | A kind of method that network traffics are quickly distributed | |
| Gutterman et al. | RAN resource usage prediction for a 5G slice broker | |
| Ruan et al. | Machine learning-based bandwidth prediction for low-latency H2M applications | |
| Wang et al. | Multimedia communications over cognitive radio networks for smart grid applications | |
| CN104219167B (en) | Network resource scheduling method and server | |
| US11546806B2 (en) | Communication system | |
| CN103532873B (en) | flow control policy applied to distributed file system | |
| Zhou et al. | Bandwidth slicing in software-defined 5G: A stackelberg game approach | |
| CN105897612B (en) | A kind of method and system based on the distribution of SDN multi service dynamic bandwidth | |
| CN111953510A (en) | Smart grid slice wireless resource allocation method and system based on reinforcement learning | |
| CN102647760B (en) | Multi-service-network-based efficient service resource management method | |
| CN104427625A (en) | Network resource scheduling method and system based on user experience | |
| CN106027288A (en) | Communication traffic prediction method for distribution line information monitoring service | |
| CN110784779A (en) | Data acquisition method of electricity consumption information acquisition system | |
| CN113364682B (en) | Data transmission method and device, storage medium and electronic device | |
| Zhang et al. | An application-oriented fair resource allocation scheme for EPON | |
| CN103327542A (en) | QoS guarantee method and device applied to MSNET network | |
| Beshley et al. | Improving the efficiency of LTE spectral resources use by introducing the new of M2M/IoT multi-service gateway | |
| CN104093209A (en) | Dynamic cognitive network resource allocating method | |
| Ruan et al. | Machine learning based bandwidth prediction in tactile heterogeneous access networks | |
| CN101795233A (en) | Method and equipment for controlling quality of service (QoS) | |
| CN103096386B (en) | Data business flow control method based on signaling analyzing | |
| Radzi et al. | Context aware traffic scheduling algorithm for power distribution smart grid network | |
| CN103874133A (en) | Method and device for bandwidth control and access point |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |