CN113747597A - Network data packet scheduling method and system based on mobile 5G network - Google Patents
Network data packet scheduling method and system based on mobile 5G network Download PDFInfo
- Publication number
- CN113747597A CN113747597A CN202111002936.4A CN202111002936A CN113747597A CN 113747597 A CN113747597 A CN 113747597A CN 202111002936 A CN202111002936 A CN 202111002936A CN 113747597 A CN113747597 A CN 113747597A
- Authority
- CN
- China
- Prior art keywords
- network bandwidth
- data
- network
- scheduling
- module
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000007635 classification algorithm Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 239000002699 waste material Substances 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 description 22
- 230000005540 biological transmission Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007618 network scheduling algorithm Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- HRULVFRXEOZUMJ-UHFFFAOYSA-K potassium;disodium;2-(4-chloro-2-methylphenoxy)propanoate;methyl-dioxido-oxo-$l^{5}-arsane Chemical compound [Na+].[Na+].[K+].C[As]([O-])([O-])=O.[O-]C(=O)C(C)OC1=CC=C(Cl)C=C1C HRULVFRXEOZUMJ-UHFFFAOYSA-K 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/56—Allocation or scheduling criteria for wireless resources based on priority criteria
- H04W72/566—Allocation or scheduling criteria for wireless resources based on priority criteria of the information or information source or recipient
- H04W72/569—Allocation or scheduling criteria for wireless resources based on priority criteria of the information or information source or recipient of the traffic information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/18—Negotiating wireless communication parameters
- H04W28/20—Negotiating bandwidth
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/535—Allocation or scheduling criteria for wireless resources based on resource usage policies
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a network data packet scheduling method based on a mobile 5G network, which comprises the following steps: step 1: the network bandwidth monitor module sends real-time network bandwidth data to a queue of the scheduling controller module at regular time; step 2: the scheduling controller module judges whether the queue is full and inserts the latest numerical value; and step 3: calculating the obtained real-time network bandwidth data; and 4, step 4: determining the current latest network bandwidth state level according to the calculation result; and 5: judging whether the network bandwidth state hierarchy changes; step 6: if the network bandwidth state hierarchy changes, a scheduler module is informed to switch a corresponding scheduling strategy; and 7: and repeating the steps 1-6, obtaining the latest network bandwidth state level in real time and adjusting the scheduling strategy in time.
Description
Technical Field
The invention relates to the field of network data packet scheduling, in particular to a network data packet scheduling method and system based on a mobile 5G network.
Background
The data packet scheduling refers to a decision process for selecting which data packets should be served or discarded, and a network scheduler, also called a data packet scheduler, is a decision maker on a node in a data packet communication network, manages a network data packet sequence in a sending and receiving queue of a network interface controller, and has a plurality of network schedulers available for different operating systems, which implement a plurality of existing network scheduling algorithms, but the current network scheduling still has a lot of defects for a mobile network, and needs to reasonably design a data packet scheduler framework, implement a multi-level network bandwidth structure, and add corresponding parameters in the whole multi-level data packet scheduling framework, so that not only can a user reasonably configure the whole data packet scheduling system according to needs, network bandwidth states and system conditions, but also can make different schedulers apply to network bandwidths of different levels, in addition, considering that different scheduling strategies have certain advantages and disadvantages under corresponding network bandwidths, the fact that the same scheduling strategy is always used under all network bandwidths is obviously not suitable, a better scheduling strategy scheme needs to be made, different data packet scheduling strategies are made under the network bandwidths of different levels, the throughput under the high network bandwidth state is guaranteed, the delay of the high-priority data packets under the network bandwidth state is reduced, and the scheduling strategy optimization is carried out on the network bandwidths of all levels.
Disclosure of Invention
The present invention is directed to provide a network packet scheduling method based on a mobile 5G network to overcome the above-mentioned drawbacks of the prior art.
The purpose of the invention can be realized by the following technical scheme:
a network data packet scheduling method based on a mobile 5G network comprises the following steps:
step 1: the network bandwidth monitor module sends real-time network bandwidth data to a queue of the scheduling controller module at regular time;
step 2: the scheduling controller module judges whether the queue is fully arranged, if the queue is fully arranged, the oldest numerical value in the queue is removed first, and then a new numerical value is inserted, and if the queue is not fully arranged, the newest numerical value is directly inserted at the tail part;
and step 3: calculating the obtained real-time network bandwidth data;
and 4, step 4: determining the current latest network bandwidth state level according to the calculation result according to the pre-grading of the network bandwidth state;
and 5: judging whether the obtained latest network bandwidth state hierarchy changes;
step 6: if the network bandwidth state hierarchy is not changed, a scheduler module is not required to be notified, all scheduling strategies are maintained to be unchanged, and if the network bandwidth state hierarchy is changed, the scheduler module is notified to select and switch the corresponding scheduling strategy of the network bandwidth state hierarchy;
and 7: and repeating the steps 1-6, acquiring the latest network bandwidth state level in real time, and adjusting the corresponding scheduling strategy in time according to the latest network bandwidth state level.
In the step 1, when the network condition is that the network bandwidth is stable, a method of setting a long interval time is adopted to avoid unnecessary state updating and waste of system resources, and when the network condition is that the network bandwidth is unstable, a method of setting a short interval time is adopted to update and reflect the change of the network bandwidth state.
In the step 2, a queue configured according to the requirement is arranged in the scheduling controller module and used for placing the real-time network bandwidth data received from the network bandwidth monitor module.
In step 3, the calculation method for calculating the obtained real-time network bandwidth data includes:
obtaining a network bandwidth state level by performing average calculation on real-time network bandwidth data in a queue;
the network bandwidth status level is obtained by performing a weighted average calculation on the real-time network bandwidth data in the queue.
In step 4, the network bandwidth status is classified in advance according to user requirements, current network conditions and system load capacity.
In the step 6, the scheduling policy algorithm of the scheduler module includes a FIFO algorithm, a PQ algorithm and a WFQ algorithm, and the scheduler module is interconnected through a link according to requirements.
The FIFO algorithm specifically comprises the following steps: treating all message data packets indiscriminately, adopting a first-in first-out strategy for processing the data packets, namely allocating resources required for forwarding according to the arrival sequence of the data packets, wherein all the data packets share network resources, the obtained resource amount and speed depend on the arrival time of the data packets, and the method is suitable for services insensitive to bandwidth and delay;
the PQ algorithm specifically comprises the following steps: in the process of scheduling the data packets, the data packets in the high-priority queue are sent preferentially according to the sequence of the priority from high to low, and the data packets in the next priority queue are processed when the high-priority queue is empty so as to process the data packets of the key service preferentially;
the WFQ algorithm is specifically as follows: when calculating a scheduling order, enabling a high-priority data packet to obtain a higher chance of priority scheduling than a low-priority data packet, automatically classifying the flows according to the conversation information of the flows, uniformly placing each flow into different queues, distributing the bandwidth proportion occupied by each flow according to the priority of the flow when dequeuing, taking out a corresponding number of data packets from the queues according to the bandwidth proportion, and sending the data packets so as to share network resources fairly and balance the delay of each flow on the whole;
the session information of the stream includes a protocol type, source and destination TCP or UDP port numbers, source and destination IP addresses, and a priority bit in the ToS domain, and the bandwidth proportion occupied by each stream is:
wherein, the total bandwidth quota is the sum of the priority of each stream plus one.
A system of network data packet scheduling method based on mobile 5G network includes:
a network bandwidth monitor module: the system is used for monitoring the network bandwidth in real time and sending the network bandwidth to the scheduling controller module;
a scheduling controller module: the system comprises a scheduler module, a data flow classification module, a data flow monitoring module and a data flow monitoring module, wherein the system is used for calculating real-time network bandwidth data sent by the network bandwidth monitoring module, acquiring a current network bandwidth state level and connecting and communicating with each scheduler module and the data flow classification module;
a data flow classification module: classifying different input data stream categories through a flow classification algorithm according to the characteristics of the data streams, effectively arranging and distributing the data streams by using a corresponding arrangement algorithm according to the current network bandwidth state hierarchy, and inputting the data streams to a scheduler module.
A scheduler module: the system comprises a plurality of scheduler modules, wherein various scheduling strategies are built in one scheduling module so as to implement the corresponding scheduling strategies according to the current network bandwidth state.
The scheduler module selects a corresponding arrangement algorithm and a scheduling strategy to effectively arrange and distribute the data streams after the data stream classification module classifies the data streams according to the network bandwidth state hierarchy, wherein the data stream categories comprise large streams, small streams, video streams, voice streams, information streams and instruction data, and different data streams have different distribution priority levels.
Compared with the prior art, the invention has the following advantages:
the problem of dealing with the scheduling of the mobile 5G network data packet is solved by using the technology of the hierarchical network bandwidth state, and the scheduling is more flexible and richer in function compared with the traditional data packet scheduling; the user can flexibly configure the scheduler in the scheduler module, can select a corresponding scheduling strategy in the scheduler module according to the network bandwidth state, set the network bandwidth state grade, and flexibly configure each parameter of the scheduling system architecture to meet the requirement; the method and the device facilitate the user to set and manage parameters according to the requirement of the user, ensure the throughput of all data packet transmission in a good network bandwidth state, and effectively ensure the delay rate of high-priority data packets and the efficiency of obtaining services in a bad network bandwidth state.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a schematic diagram of the system of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
Examples
As shown in fig. 1, the present invention provides a network packet scheduling system based on a mobile 5G network, wherein: the network bandwidth monitor module monitors the network bandwidth in real time and is in communication connection with the scheduling controller module; the scheduling controller module obtains the current network bandwidth state hierarchy through calculation and is connected and communicated with the scheduler module and the data flow classification module; the scheduler module is internally provided with various preset scheduling strategies; the data flow classification module is used for classifying different network data flows, and the data flow classification module only classifies the data flows under specific conditions so as to enable the scheduling module to schedule the data flows according to the data flow categories, wherein each module is connected through a data transmission link and provides a channel for data transmission among the modules.
A plurality of scheduler modules are built in the same data packet scheduling system, and each scheduler module can implement a corresponding network scheduling strategy according to the network bandwidth state, so that the network scheduling strategies on all the scheduler modules can be modified and configured according to requirements while the same network flexibly selects the scheduling strategies under different network bandwidth states.
The network bandwidth state refers to: in the process of continuous movement of the device, the received network signal strength is continuously changed, and the network bandwidth value is also continuously changed, so that the network bandwidth state is divided into a plurality of levels, each level represents the bandwidth state of the corresponding network, for example, a 500m/s network can be divided into three levels, which are respectively high, medium and low, high represents that the network bandwidth state is excellent, medium represents that the network bandwidth state is medium, and low represents that the network bandwidth state is not ideal.
The network bandwidth monitor sends the monitored real-time network bandwidth data to the scheduling controller module for calculation, and after a calculation result is obtained, the calculation result is broadcasted to each controlled scheduler module to be executed if necessary.
The calculation performed by the scheduling controller module is as follows: the network bandwidth monitor module sends monitored real-time network bandwidth data to the scheduling controller module at intervals, the interval time can be set, the queue service nodes know information of all communication nodes to form a queue service cluster and provide faster service, the queue service cluster is realized by adopting a message queue, the scheduling controller module puts received bandwidth values into the queue, the size of the queue can be set, when the queue is saturated, the latest data replaces the oldest data, the oldest data is discarded, the scheduling controller module calculates the average value of all element values in the queue, and if necessary, the scheduling controller module broadcasts the values to the scheduler module.
The scheduling controller module controls all scheduler modules connected with the scheduling controller module, a queue is arranged in the scheduling controller module and used for placing the bandwidth numerical value received from the network bandwidth monitor module, the size of the queue can be configured according to requirements, the controller calculates the average value in the queue, and when the average value calculated by the controller is different from the bandwidth range of the current network bandwidth state, the controller informs the scheduler module to switch the scheduling strategy corresponding to the current state.
The flow classification algorithm specifically comprises the following steps: the method is characterized in that different network data streams are classified, wherein the different streams comprise large streams, small streams, video streams, voice streams, information streams, instruction data and the like, the different streams have different distribution priority levels, the streams are effectively distributed by using a corresponding arrangement algorithm and a corresponding scheduling strategy according to the current network bandwidth state level, and for example, the important and high-priority data streams such as instructions are arranged in the front of a queue to be preferentially processed and distributed when the network state level is low and the network bandwidth state is not good.
Each scheduler module, which may contain scheduling policy algorithms such as FIFO, PQ and WFQ algorithms, may be interconnected by links and then on demand.
FIFO algorithm: all message data packets are treated indiscriminately, a first-in first-out strategy is adopted by a scheduler module for processing the data packets, resources required by forwarding are distributed according to the sequence of arrival of the data packets, all the data packets share network resources, the quantity and speed of the obtained resources are completely dependent on the arrival time of the data packets, the service strategy is simple and easy, the calculation requirement is not high, but no guarantee is provided for delay, delay jitter, packet loss rate and the like, under the condition that network bandwidth resources are insufficient, smooth transmission of high-priority data packets cannot be guaranteed, and the method is only suitable for services insensitive to bandwidth and delay;
PQ algorithm (priority queue): PQ queues are designed for critical business applications, i.e., high priority packets are required to be serviced first. In the process of scheduling data packets, the PQ preferentially sends the data packets in the high-priority queue according to the sequence of the priority from high to low strictly, and processes the data packets in the next-level priority queue when the high-priority queue is empty, the scheduling strategy has the advantages that the data packets of the key service can be preferentially processed, and the defect is obvious, namely, if the data packets exist in the high-priority queue all the time, the data packets in the low-priority queue can not be served until starved;
WFQ Algorithm (weighted average queue, WeightedFairQueueing): the FQ is introduced to fairly share network resources to optimize delay and delay jitter of all streams as much as possible, and is mainly expressed as follows: the different queues get a fair scheduling opportunity, balancing the delay of the individual flows as a whole. Compared with the FQ, the WFQ considers the problem of priority in calculating the scheduling order, and statistically, the WFQ makes the high-priority packet get more chance to be scheduled preferentially than the low-priority packet, and can automatically classify the flows according to the session information of the flows (including protocol type, source and destination TCP or UDP port number, source and destination IP address, and priority bit in ToS domain, etc.), and provide queues as many as possible to put each flow into different queues uniformly, so as to equalize the delay of each flow as a whole, and when dequeuing, the WFQ allocates the bandwidth that each flow should occupy the egress according to the priority (precedence or DSCP) of the flow: the smaller the value of the priority, the less bandwidth is obtained. The larger the value of the priority is, the more the bandwidth is obtained, and finally, each queue is polled, and a corresponding number of data packets are taken out from the queue according to the bandwidth ratio for transmission, for example: there are currently 5 flows in the interface, their priorities are 0, 1, 2, 3, and 4, respectively, that is, 1+2+3+4+5 is 15, and the bandwidth ratio occupied by each flow is: (priority number of stream + 1)/total bandwidth quota, wherein the total bandwidth quota is the sum of the priority of each stream plus one, and the available bandwidth of each stream is obtained as follows: 1/15, 2/15, 3/15, 4/15, 5/15 suffer from computational complexity, higher hardware requirements, and inability to dynamically configure bandwidth allocation parameters in accordance with changes in network bandwidth conditions.
The invention adopts a network bandwidth state grading mixed scheduling method to schedule the data packet: the scheduling controller module calculates real-time network bandwidth data sent by the network bandwidth monitor module, calculates the hierarchy of the current network bandwidth state, and when the hierarchy changes, informs all the scheduler modules and the data stream classification module of new hierarchy information, and the data stream classification module automatically enables the scheduler modules to select corresponding scheduling strategies through the network bandwidth state hierarchy obtained from the scheduling controller module, so that the corresponding scheduler modules are repeatedly selected for the current network bandwidth state hierarchy.
As shown in fig. 2, the process of the method specifically includes:
step 1: the network bandwidth monitor module sends real-time network bandwidth data to a queue of the scheduling controller module at regular time, and time intervals are set according to actual conditions;
step 2: judging whether the queue is full, if the queue is full, firstly removing the oldest numerical value (namely the head numerical value of the queue) in the queue, and then inserting a new numerical value; if the queue is not full, directly inserting the latest numerical value at the tail part;
and step 3: calculating their average or weighted average for all values in the queue;
and 4, step 4: and determining the current latest network bandwidth state hierarchy (classifying the network bandwidth state in advance) according to the average value (the network bandwidth average value) obtained by calculation.
And 5: judging whether the latest network bandwidth state hierarchy changes and the current network bandwidth state hierarchy does not conform according to the acquired latest network bandwidth state hierarchy;
step 6: if the network bandwidth state hierarchy is not changed, the scheduler module does not need to be notified, and all scheduling strategies are kept unchanged; if the network bandwidth state level changes, the scheduler module is notified to select and switch the scheduling policy of the corresponding network bandwidth state level, for example, if the network bandwidth state level changes to 2, the scheduler module switches to the preset scheduling policy of level 2.
And 7: and returning to the step 1, repeatedly and timely acquiring the latest network bandwidth state level, and performing corresponding action and adjustment according to the latest network bandwidth state level.
For example: a500 m/s network is divided into three levels, namely high, medium and low, a scheduling controller module informs a scheduler module when the network bandwidth state level is low, a data flow classification module classifies different network data flows, important and high-priority data flows such as instructions are arranged in the front of a queue, and then the data flows are transmitted to the scheduler module to be processed by calling a flow classification algorithm.
The parameters of the network bandwidth state grading mixed scheduling method comprise: the interval time sent to the scheduling controller module by the network bandwidth monitor module; the size of a queue for storing real-time network bandwidth data in a scheduling controller module; calculating a network bandwidth state classification calculation method; the number of levels of network bandwidth status classification, etc.
The interval time parameter sent by the network bandwidth monitor module to the scheduling controller module is: the method comprises the steps of setting how long to send real-time network bandwidth data to a scheduling controller module, wherein the longer the interval time setting means that the updating of the network bandwidth state is rarer and slower, and on the other hand, the shorter the interval time setting means that queues in the scheduling controller module are frequently replaced, meanwhile, the updating of the network bandwidth state is more frequent.
The scheduling controller module stores the queue size of the bandwidth value: setting the amount of allowable bandwidth values to be placed in a queue, wherein the larger the setting queue is, the more bandwidth values can participate in the calculation of the network bandwidth state classification, and the smaller the setting queue is, the less bandwidth values can influence the calculation and classification of the network bandwidth state; generally, the larger the queue is, the accuracy of the network bandwidth state classification calculation can be ensured, but at the same time, larger resource overhead and untimely network bandwidth state classification calculation are also caused, and the smaller the queue is, the opposite is true, so that the size of the queue needs to be set according to the requirements and actual conditions of users.
The calculation method of the network bandwidth state classification comprises the following steps: the numerical values in the queue are calculated, the level of the current network bandwidth state is calculated, and the average number of the numerical values in the queue can be calculated to obtain the level of the network bandwidth state, which is the simplest and direct mode; in addition, the numerical values in the queues can be calculated by using weighted average, the specific method is that the weight of the numerical value which is added more newly is higher, the level of the network bandwidth state is calculated by analogy in turn, the calculation method is more reasonable, the calculation is more complex, and meanwhile, more calculation resources are consumed, so the method is recommended to be used when the queue setting is larger, and the calculation method is used according to the requirements and actual conditions of users.
Number of stages of network bandwidth status classification: i.e. the network bandwidth status is divided into several levels, for example: with a network bandwidth of 500m/s, this network bandwidth can be divided into 5 levels: 0-100m/s, 100-200m/s, 200-300m/s, 300-400m/s and 400-500 m/s; it can also be divided into 3 stages: 0-200m/s, 200-400m/s and 400-500 m/s. The specific grading mode is selected according to the network bandwidth, and generally, the larger the network bandwidth is, the more the network grading is, and vice versa, the less the network grading is; the more unstable the network bandwidth state, the more the network classification, and vice versa, the less; the finer the network bandwidth state classification is, the more the change of the network bandwidth state can be captured through the classification calculation, so that the corresponding adjustment is made to the scheduling policy quickly to adapt to the current network bandwidth state, however, the too fine network bandwidth state classification indicates that the network bandwidth state is updated frequently, which causes the network scheduling policy to be switched continuously, meanwhile, the scheduling policy of the corresponding level is more and more complex, the cost in the aspects of calculation and the like is more, so that the pressure of the whole system is too large, and a good effect cannot be obtained, therefore, the setting of the specific network bandwidth state level needs to be determined according to the user requirement, the current network state and the load capacity of the system.
The invention firstly grades the network bandwidth state, acquires the network bandwidth state hierarchy by the calculation of the scheduling controller module, calculates different network bandwidth states, secondly embeds a plurality of different scheduling strategies in the scheduler module, and can automatically select the corresponding data packet scheduling strategy according to the requirements of users and the current network bandwidth state so as to achieve the purposes of the users and optimize the transmission of data packets.
Through specific practical experiments, under the test environment that the peak value of the network bandwidth is 500m/s and the network bandwidth changes, the method and the system provided by the invention have the following experimental effects: the method not only ensures the throughput of data transmission under the condition of better network bandwidth state, but also meets the low-delay requirement of high-priority data packets under the condition of poorer network bandwidth, and obtains better effect under the condition of taking both the two aspects into consideration.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and those skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A network data packet scheduling method based on a mobile 5G network is characterized by comprising the following steps:
step 1: the network bandwidth monitor module sends real-time network bandwidth data to a queue of the scheduling controller module at regular time;
step 2: the scheduling controller module judges whether the queue is fully arranged, if the queue is fully arranged, the oldest numerical value in the queue is removed first, and then a new numerical value is inserted, and if the queue is not fully arranged, the newest numerical value is directly inserted at the tail part;
and step 3: calculating the obtained real-time network bandwidth data;
and 4, step 4: determining the current latest network bandwidth state level according to the calculation result according to the pre-grading of the network bandwidth state;
and 5: judging whether the obtained latest network bandwidth state hierarchy changes;
step 6: if the network bandwidth state hierarchy is not changed, a scheduler module is not required to be notified, all scheduling strategies are maintained to be unchanged, and if the network bandwidth state hierarchy is changed, the scheduler module is notified to select and switch the corresponding scheduling strategy of the network bandwidth state hierarchy;
and 7: and repeating the steps 1-6, acquiring the latest network bandwidth state level in real time, and adjusting the corresponding scheduling strategy in time according to the latest network bandwidth state level.
2. The method as claimed in claim 1, wherein in step 1, when the network condition is that the network bandwidth is stable, the method for setting the long interval time is adopted to avoid unnecessary status update and waste of system resources, and when the network condition is that the network bandwidth is unstable, the method for setting the short interval time is adopted to update and reflect the change of the network bandwidth status.
3. The method as claimed in claim 1, wherein in step 2, the scheduling controller module has a queue with a size configured according to a requirement for placing the real-time network bandwidth data received from the network bandwidth monitor module.
4. The method as claimed in claim 3, wherein the step 3 of calculating the obtained real-time network bandwidth data includes:
obtaining a network bandwidth state level by performing average calculation on real-time network bandwidth data in a queue;
the network bandwidth status level is obtained by performing a weighted average calculation on the real-time network bandwidth data in the queue.
5. The method as claimed in claim 1, wherein in step 4, the network bandwidth status is classified in advance according to user requirements, current network conditions and system load capacity.
6. The method as claimed in claim 1, wherein in step 6, the scheduling policy algorithm of the scheduler module includes a FIFO algorithm, a PQ algorithm and a WFQ algorithm, and the scheduler module is interconnected through a link according to requirements.
7. The method according to claim 6, wherein the FIFO algorithm specifically comprises: treating all message data packets indiscriminately, adopting a first-in first-out strategy for processing the data packets, namely allocating resources required for forwarding according to the arrival sequence of the data packets, wherein all the data packets share network resources, the obtained resource amount and speed depend on the arrival time of the data packets, and the method is suitable for services insensitive to bandwidth and delay;
the PQ algorithm specifically comprises the following steps: in the process of scheduling the data packets, the data packets in the high-priority queue are sent preferentially according to the sequence of the priority from high to low, and the data packets in the next priority queue are processed when the high-priority queue is empty so as to process the data packets of the key service preferentially;
the WFQ algorithm is specifically as follows: when the scheduling order is calculated, the probability of obtaining priority scheduling for the data packets with high priority is higher than that of the data packets with low priority, flow classification is automatically carried out according to the conversation information of the flows, each flow is uniformly placed into different queues, the bandwidth proportion occupied by each flow is distributed according to the priority of the flow when dequeuing, the data packets with corresponding quantity are taken out from the queues according to the bandwidth proportion and sent, and therefore network resources are shared fairly and the delay of each flow is balanced on the whole.
8. The method as claimed in claim 7, wherein the session information of the flow includes protocol type, source and destination TCP or UDP port number, source and destination IP address and priority bit in ToS domain, and the ratio of bandwidth occupied by each flow is:
wherein, the total bandwidth quota is the sum of the priority of each stream plus one.
9. A system for implementing a network packet scheduling method based on a mobile 5G network according to any of claims 1 to 8, the system comprising:
a network bandwidth monitor module: the system is used for monitoring the network bandwidth in real time and sending the network bandwidth to the scheduling controller module;
a scheduling controller module: the system comprises a scheduler module, a data flow classification module, a data flow monitoring module and a data flow monitoring module, wherein the system is used for calculating real-time network bandwidth data sent by the network bandwidth monitoring module, acquiring a current network bandwidth state level and connecting and communicating with each scheduler module and the data flow classification module;
a data flow classification module: classifying different input data stream categories through a flow classification algorithm according to the characteristics of the data streams, effectively arranging and distributing the data streams by using a corresponding arrangement algorithm according to the current network bandwidth state hierarchy, and inputting the data streams to a scheduler module;
a scheduler module: the system comprises a plurality of scheduler modules, wherein various scheduling strategies are built in one scheduling module so as to implement the corresponding scheduling strategies according to the current network bandwidth state.
10. The system according to claim 9, wherein the scheduler module selects a corresponding arrangement algorithm and scheduling policy to perform efficient arrangement and distribution on the data streams after the data stream classification module classifies the data streams according to the network bandwidth state hierarchy selection, the data stream categories include large streams, small streams, video streams, voice streams, information streams and instruction data, and different data streams have different distribution priority levels.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111002936.4A CN113747597A (en) | 2021-08-30 | 2021-08-30 | Network data packet scheduling method and system based on mobile 5G network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111002936.4A CN113747597A (en) | 2021-08-30 | 2021-08-30 | Network data packet scheduling method and system based on mobile 5G network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113747597A true CN113747597A (en) | 2021-12-03 |
Family
ID=78733832
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111002936.4A Pending CN113747597A (en) | 2021-08-30 | 2021-08-30 | Network data packet scheduling method and system based on mobile 5G network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113747597A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115396384A (en) * | 2022-07-28 | 2022-11-25 | 广东技术师范大学 | Data packet scheduling method, system and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040143663A1 (en) * | 2002-08-14 | 2004-07-22 | Leedom David Arlen | Method and apparatus for monitoring and controlling the allocation of network bandwidth |
CN1518296A (en) * | 2003-01-13 | 2004-08-04 | 华为技术有限公司 | Method of implementing integrated queue scheduling for supporting multi service |
US20050094643A1 (en) * | 2003-11-05 | 2005-05-05 | Xiaolin Wang | Method of and apparatus for variable length data packet transmission with configurable adaptive output scheduling enabling transmission on the same transmission link(s) of differentiated services for various traffic types |
US20070127410A1 (en) * | 2005-12-06 | 2007-06-07 | Jianlin Guo | QoS for AV transmission over wireless networks |
US20080133744A1 (en) * | 2006-12-01 | 2008-06-05 | Ahn Shin Young | Multimedia data streaming server and method for dynamically changing amount of transmitting data in response to network bandwidth |
JP2013179678A (en) * | 2013-05-13 | 2013-09-09 | Yamaha Corp | Router device |
CN103841052A (en) * | 2012-11-27 | 2014-06-04 | 中国科学院声学研究所 | Bandwidth resource distribution system and method |
US20140355427A1 (en) * | 2013-06-04 | 2014-12-04 | Netgear, Inc. | System and method for providing dynamic qos to maximize bandwidth utilization |
US20150326481A1 (en) * | 2014-05-09 | 2015-11-12 | Nexgen Storage, Inc. | Adaptive bandwidth throttling |
CN105636224A (en) * | 2015-05-28 | 2016-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Network resource optimization method and device and wireless access point |
CN108156093A (en) * | 2018-01-25 | 2018-06-12 | 中科边缘智慧信息科技(苏州)有限公司 | Data transmission method and system are applied suitable for low bandwidth Weak link environment more |
-
2021
- 2021-08-30 CN CN202111002936.4A patent/CN113747597A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040143663A1 (en) * | 2002-08-14 | 2004-07-22 | Leedom David Arlen | Method and apparatus for monitoring and controlling the allocation of network bandwidth |
CN1518296A (en) * | 2003-01-13 | 2004-08-04 | 华为技术有限公司 | Method of implementing integrated queue scheduling for supporting multi service |
US20050094643A1 (en) * | 2003-11-05 | 2005-05-05 | Xiaolin Wang | Method of and apparatus for variable length data packet transmission with configurable adaptive output scheduling enabling transmission on the same transmission link(s) of differentiated services for various traffic types |
US20070127410A1 (en) * | 2005-12-06 | 2007-06-07 | Jianlin Guo | QoS for AV transmission over wireless networks |
US20080133744A1 (en) * | 2006-12-01 | 2008-06-05 | Ahn Shin Young | Multimedia data streaming server and method for dynamically changing amount of transmitting data in response to network bandwidth |
CN103841052A (en) * | 2012-11-27 | 2014-06-04 | 中国科学院声学研究所 | Bandwidth resource distribution system and method |
JP2013179678A (en) * | 2013-05-13 | 2013-09-09 | Yamaha Corp | Router device |
US20140355427A1 (en) * | 2013-06-04 | 2014-12-04 | Netgear, Inc. | System and method for providing dynamic qos to maximize bandwidth utilization |
US20150326481A1 (en) * | 2014-05-09 | 2015-11-12 | Nexgen Storage, Inc. | Adaptive bandwidth throttling |
CN105636224A (en) * | 2015-05-28 | 2016-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Network resource optimization method and device and wireless access point |
CN108156093A (en) * | 2018-01-25 | 2018-06-12 | 中科边缘智慧信息科技(苏州)有限公司 | Data transmission method and system are applied suitable for low bandwidth Weak link environment more |
Non-Patent Citations (2)
Title |
---|
许飞: ""基于区分服务的QoS调度策略研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
邹盟军, 曹健雄: "电力信息网络的服务质量策略", 电力***自动化, no. 13, pages 4 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115396384A (en) * | 2022-07-28 | 2022-11-25 | 广东技术师范大学 | Data packet scheduling method, system and storage medium |
CN115396384B (en) * | 2022-07-28 | 2023-11-28 | 广东技术师范大学 | Data packet scheduling method, system and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8638664B2 (en) | Shared weighted fair queuing (WFQ) shaper | |
US7027457B1 (en) | Method and apparatus for providing differentiated Quality-of-Service guarantees in scalable packet switches | |
EP1345365A2 (en) | Weighted fair queuing (WFQ) shaper | |
US7983287B2 (en) | Backpressure mechanism for switching fabric | |
US6678248B1 (en) | Policy based quality of service | |
US6859438B2 (en) | Policy based quality of service | |
JP5365415B2 (en) | Packet relay apparatus and congestion control method | |
US8144588B1 (en) | Scalable resource management in distributed environment | |
EP2302843A1 (en) | Method and device for packet scheduling | |
CN107454015B (en) | OF-DiffServ model-based QoS control method and system | |
CN104079501A (en) | Queue scheduling method based on multiple priorities | |
CN107579921B (en) | Flow control method and device | |
US8665719B2 (en) | Variable packet-size backplanes for switching and routing systems | |
US6947380B1 (en) | Guaranteed bandwidth mechanism for a terabit multiservice switch | |
CN108156093A (en) | Data transmission method and system are applied suitable for low bandwidth Weak link environment more | |
CN113747597A (en) | Network data packet scheduling method and system based on mobile 5G network | |
CN106330710B (en) | Data stream scheduling method and device | |
US11463370B2 (en) | Scalable deterministic services in packet networks | |
KR100545793B1 (en) | Scheduling Method and Device in Dynamic Multichannel Environment | |
Kaur et al. | Core-stateless guaranteed throughput networks | |
CN110247859A (en) | A kind of data transmission method for uplink and device based on AIRT-ROS node | |
US8467401B1 (en) | Scheduling variable length packets | |
CN102769566A (en) | Method and device for configuring multilevel scheduling system, and method and device for changing configuration of multilevel scheduling system | |
EP1458149A2 (en) | System and method for scheduling data traffic flows for a communication device | |
Asaduzzaman et al. | The Eight Class of Service Model-An Improvement over the Five Classes of Service |
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 |