CN114268537A - Network slice generation and dynamic configuration system and method for deterministic network - Google Patents
Network slice generation and dynamic configuration system and method for deterministic network Download PDFInfo
- Publication number
- CN114268537A CN114268537A CN202111424669.XA CN202111424669A CN114268537A CN 114268537 A CN114268537 A CN 114268537A CN 202111424669 A CN202111424669 A CN 202111424669A CN 114268537 A CN114268537 A CN 114268537A
- Authority
- CN
- China
- Prior art keywords
- network
- deterministic
- module
- slice
- traffic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 33
- 230000005540 biological transmission Effects 0.000 claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims description 35
- 238000005259 measurement Methods 0.000 claims description 20
- 230000003068 static effect Effects 0.000 claims description 18
- 230000002787 reinforcement Effects 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 11
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 4
- 238000002347 injection Methods 0.000 claims description 4
- 239000007924 injection Substances 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 230000001172 regenerating effect Effects 0.000 claims description 3
- 230000008929 regeneration Effects 0.000 claims description 3
- 238000011069 regeneration method Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 239000000243 solution Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000002955 isolation Methods 0.000 description 3
- 235000019580 granularity Nutrition 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Abstract
The invention relates to the field of Internet, and discloses a network slice generation and dynamic configuration system and method for a deterministic network. The network slice generation and dynamic configuration system for the deterministic network comprises an information acquisition module, a software control module and a network transmission module. The network slice generation and dynamic configuration method ensures bandwidth resources of deterministic services by dividing link space of a network layer, realizes division of network slices by a network slice algorithm, realizes network resource reservation and division based on deterministic service flows, avoids network congestion queuing and resource robbery generated by a plurality of deterministic data flows simultaneously reaching an end node by scheduling time slots of flow in a deterministic network virtual slice, divides the bandwidth of the deterministic services from a time dimension, increases flexibility of the slices by the time slots, and can adjust through the time slots without resetting the slices if the services are different.
Description
Technical Field
The invention relates to the field of internet, in particular to a network slice generation and dynamic configuration system and method for a deterministic network.
Background
At present, with the increasing application quantity of industry 4.0, remote driving, remote operation and the like, the requirements on network ultra-low time delay and micro jitter are higher and higher. The industrial Internet of things requires that the end-to-end time delay is microsecond to millisecond, and the jitter is microsecond; the touch internet (remote operation) requires that the end-to-end time delay is 3-10 ms, and the jitter is not more than 2 ms; the auxiliary driving requires that the end-to-end time delay is 100-250 mu s, and the jitter is several microseconds. Remote driving requires not only low delay jitter but also higher transmission rates. In order to meet the requirements of the applications on the network, a Time Sensitive Network (TSN) and a deterministic network (DetNet) respectively optimize a link layer and a network layer of the ethernet, and improve the support capability of the time sensitive network to time sensitive streaming transmission.
The definition of determinism in the network 5.0 means that besides the forwarding capability of the IP network "best effort", an all-round determinism capability guarantee including determinism time delay, determinism jitter and determinism path is provided to meet the severe requirement of future service on the network quality. In order to guarantee deterministic traffic requirements, the DetNet optimizes the ethernet L3 layer from the three aspects of time certainty, resource certainty and path certainty. The resource reservation in the key technology of resource certainty relates to resource allocation, resource isolation and the like. The Network slice can reasonably allocate the device resources through NFV (Network Function Virtualization), convert the device resources into a plurality of end-to-end Network slices with different granularities and high isolation, and virtualize a plurality of mutually insulated subnet slices respectively adapting to different services in a networking mode according to needs.
At present, no concept related to slices is proposed in the field of deterministic networks, but many studies on resource reservation for guaranteeing Qos service quality and studies on slices have been proposed in 5G in the network, most of which only achieve simple isolation between virtualized slices and services, many of which do not consider service differences of slices and fairness between different services, and most of which achieve allocation of network resources from historical statistics of traffic requests but do not combine perception of current traffic flows, and that is, resources are allocated only by using network future load states predicted by a simple statistical method, which is not in line with the concept of deterministic traffic precedence in deterministic networks.
In summary, the current network slicing method based on the deterministic network has the following problems:
1. characteristics of deterministic traffic, differentiation of traffic services and fairness between different services are not taken into account
2. The deterministic traffic priority idea is not considered, and the dynamic slicing adjustment is not considered.
3. The burst situation of the deterministic traffic and the class situation of the traffic are not considered, and the slicing has no flexibility.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a deterministic network-oriented network slice generation and dynamic configuration system and method, so as to overcome the defects and drawbacks of the prior art.
In order to solve the above technical problem, the present invention provides a deterministic network-oriented network slice generation and dynamic configuration system, which mainly comprises: the system comprises an information acquisition module, a software control module and a network transmission module;
and the information acquisition module is used for acquiring the information of the network transmission module and outputting the flow information in the deterministic network to the software control module. The information acquisition module comprises a deterministic network dynamic measurement module and a deterministic network static measurement module; wherein the content of the first and second substances,
the deterministic network dynamic measurement module is used for measuring the link load state and the network flow state in the network, the obtained flow in the deterministic network is represented in a flow matrix form, and the bandwidth, time delay and jitter information required by the deterministic flow are stored and represented by a text document;
and the deterministic network static measurement module is used for measuring static information in the network, wherein the static information comprises router connection condition, port condition, link bandwidth condition and the like.
The software control module is used for determinacy network slice prediction, construction, scheduling and adjustment, and outputting information to the network transmission module; the software control module comprises a deterministic network slice prediction module, a deterministic network slice construction module, a deterministic network slice scheduling module and a deterministic network slice adjustment template; the deterministic network slice prediction module is used for predicting the deterministic network flow in a future period of time by an RNN (radio network) cyclic network method.
And the deterministic network slice construction module is used for reserving the bandwidth of the link by a deep reinforcement learning network slice method to output the occupation ratio of the deterministic network slice to the link.
And the deterministic network slice scheduling module is used for scheduling the resources in the deterministic network slice on the basis of the time slot through the required bandwidth, time delay and jitter of the real-time deterministic traffic in the network output by the measuring module.
And the deterministic network slice adjusting template is used for outputting the link real-time state through the network dynamic measuring module, and carrying out re-deterministic network slice construction if the load of the deterministic network exceeds a set threshold value.
The output end of the network transmission module is connected with the information acquisition module and the underlying network topology and is used for issuing a deterministic network flow table and configuring deterministic network slices; the network transmission module comprises a deterministic network flow table issuing module and a deterministic network slice configuration module, wherein the deterministic network flow table issuing module is used for configuring a port and issuing a flow table to a network layer through flow table information. And the deterministic network slicing configuration module is used for performing link bandwidth allocation and configuration of the deterministic switch through slicing information output by the network slicing module, wherein the deterministic switch and the non-deterministic switch are divided into two ports for configuration.
The invention also provides a network slice generation and dynamic configuration method facing the deterministic network, which comprises the following steps:
step 1: and collecting a deterministic flow data set, generating a deterministic flow matrix and needed jitter and time delay information, inputting the obtained deterministic flow matrix and related information into a depth model according to a time sequence to perform flow prediction, and performing deterministic network flow prediction.
Step 2: inputting the obtained deterministic network flow prediction data set with bandwidth, time delay and jitter requirements and topology basic information in the network into a network slicing algorithm based on reinforcement learning to form bandwidth and port information required by a deterministic slice, and configuring the deterministic network slice according to the bandwidth and port information required by the deterministic slice.
And step 3: and the resource scheduling in the deterministic slice of the time slot level is carried out by applying a bandwidth scheduling algorithm strategy of the time slot level in the deterministic network slice, so that network congestion queuing and resource robbing generated when a plurality of deterministic data streams simultaneously reach the end node are reduced in the time dimension.
And 4, step 4: calculating network profit according to link bandwidth, topology and deterministic traffic information in a network, returning to the step 1 if the network profit does not meet a certain design threshold, and carrying out regeneration and dynamic configuration of a slicing strategy; otherwise, monitoring of link bandwidth, topology, and deterministic traffic information in the network is maintained.
Preferably, step 1 comprises the following substeps:
step 1-1: collecting historical traffic data in a network by using output data of a data acquisition module, and classifying the historical traffic data according to different deterministic service requirements to form a deterministic network traffic matrix and a non-deterministic network traffic matrix;
step 1-2: modeling the formed flow matrix to obtain a flow matrix containing jitter and time delay information related information required by deterministic flow;
step 1-3: then, forecasting the deterministic traffic through an RNN (radio network) cyclic network algorithm to form a forecasting traffic matrix of the deterministic traffic with a relative time sequence;
preferably, step 2 comprises the following substeps:
step 2-1: link bandwidth sizes in a deterministic network are collected by a network resource static collection module.
Step 2-2: and (3) inputting the data set of the deterministic network traffic matrix predicted by the RNN algorithm in the step (1) into a reinforcement learning network slicing algorithm, and generating network slicing module configuration parameters of a port number and a reserved bandwidth of the deterministic network resources which can be reserved.
Step 2-3: and reserving resources on the space bandwidth of the obtained configuration parameters in a network slice configuration module of the transmission module to form an initial network slice.
Preferably, step 3 comprises the following substeps:
step 3-1: step 2, two virtual sub-networks of a deterministic network slice and a non-deterministic network slice are generated by configuring a deterministic network, and real-time deterministic network flow and types, time delay and jitter of the real-time deterministic network flow are extracted and counted by a network state measuring module;
step 3-2: according to different types of the deterministic traffic, quantizing the bandwidth in the deterministic network slice into time slots, dividing the time slots in the deterministic network for the flexibly entered deterministic traffic, and performing resource scheduling on the bandwidth in the deterministic slice by using a time slot algorithm.
Step 3-3: and adjusting the injection time of the scheduling flow in the network transmission module according to the result of the time slot algorithm division, thereby realizing the resource scheduling algorithm in the deterministic network slice based on the time slot.
Preferably, step 4 comprises the following substeps:
step 4-1: and performing state monitoring on the deterministic traffic in a deterministic network dynamic measurement module.
Step 4-2: and (4) processing the network state data monitored in the step (4-1), analyzing the network state condition, and regenerating and configuring a deterministic network slice when the bandwidth, time delay and jitter average service guarantee rate of the deterministic traffic is less than a design threshold.
The invention ensures the bandwidth resource of the deterministic service by dividing the link space of the network layer, realizes the division of the network slice by a network slice algorithm, realizes the reservation and the division of the network resource based on the deterministic service flow, avoids the network congestion queuing and the resource robbery generated by the simultaneous arrival of a plurality of deterministic data flows at the end node by scheduling the time slot of the flow in the deterministic network virtual slice, divides the bandwidth of the deterministic service from the time dimension, increases the flexibility of the slice by the time slot, and can adjust through the time slot without resetting the slice if the service is different.
Drawings
The technical solution of the present invention will be further specifically described with reference to the accompanying drawings and the detailed description.
Fig. 1 is a block diagram showing the structure of each module of the system of the present invention.
FIG. 2 is a functional logic structure diagram of the modules of the system of the present invention.
FIG. 3 is a general flow diagram of the method of the present invention.
Detailed Description
With reference to fig. 1 and 2, the deterministic network slice generating and dynamic configuration system of the present invention includes an information acquisition module, a software control module, and a network transmission module;
and the information acquisition module is used for acquiring the information of the network transmission module and outputting the flow information in the deterministic network to the software control module. The information acquisition module comprises a deterministic network dynamic measurement module and a deterministic network static measurement module; the deterministic network dynamic measurement module is used for measuring a link load state and a network flow state in a network, the obtained flow in the deterministic network is represented in a flow matrix form, and bandwidth, time delay and jitter information required by the deterministic flow are stored and represented by a text document; and the deterministic network static measurement module is used for measuring static information in the network, wherein the static information comprises router connection condition, port condition, link bandwidth condition and the like.
The software control module is used for predicting, constructing, scheduling and adjusting the deterministic network slice and outputting information to the network transmission module; the software control module comprises a deterministic network slice prediction module, a deterministic network slice construction module, a deterministic network slice scheduling module and a deterministic network slice adjustment template; the deterministic network slice prediction module is used for predicting the deterministic network flow in a future period of time by an RNN (radio network) cyclic network method. And the deterministic network slice construction module is used for reserving the bandwidth of the link by a deep reinforcement learning network slice method to output the occupation ratio of the deterministic network slice to the link. And the deterministic network slice scheduling module is used for scheduling the resources in the deterministic network slice on the basis of the time slot through the required bandwidth, time delay and jitter of the real-time deterministic traffic in the network output by the measuring module. And the deterministic network slice adjusting template is used for outputting the link real-time state through the network dynamic measuring module, and carrying out re-deterministic network slice construction if the load of the deterministic network exceeds a set threshold value.
The output end of the network transmission module is connected with the information acquisition module and the underlying network topology and is used for issuing a deterministic network flow table and configuring deterministic network slices; the network transmission module comprises a deterministic network flow table issuing module and a deterministic network slice configuration module, wherein the deterministic network flow table issuing module is used for configuring a port and issuing a flow table to a network layer through flow table information. And the deterministic network slicing configuration module is used for performing link bandwidth allocation and configuration of the deterministic switch through slicing information output by the network slicing module, wherein the deterministic switch and the non-deterministic switch are divided into two ports for configuration.
With reference to fig. 2 and 3, the deterministic network slice generation and dynamic configuration process of the present invention is as follows:
step 1: and acquiring a deterministic traffic data set from an information acquisition module, generating a deterministic traffic matrix and required jitter and time delay information, inputting the acquired deterministic traffic matrix and related information into a depth model according to a time sequence to perform traffic prediction, and performing deterministic network traffic prediction.
step 1-1: collecting historical traffic data in a network by using output data of a data acquisition module, and classifying the historical traffic data according to different deterministic service requirements to form a deterministic network traffic matrix and a non-deterministic network traffic matrix; the step 1-1 specifically comprises: obtaining a data set labeled with traffic categories in a deterministic network, wherein the data set has end-to-end traffic requirements and is labeled with all traffic categories, and the traffic categories in the deterministic network are divided into 10 categories, wherein 0, 1 and 2 are non-deterministicThe flow rate of the water is measured,3-9 are deterministicThe flow rate of the water is measured,the non-deterministic traffic is divided into background traffic, best effort traffic and best effort guarantee traffic. The deterministic traffic has different guarantees of time delay, bandwidth and jitter,no. 3The classes are computing power class and emergency support class flow;4 thLike time delay<Deterministic traffic of 100ms videoconference-like traffic;5 thLike time delay<Voice call class deterministic traffic of 10 ms;6 thThe classes are internet routing control protocol (OSPF, RIP, DNS, etc. traffic.7 thThe classes are holographic communication, VR interactive class traffic,8 thThe class is remote feedback class flow (multispectral video and sensor flow in industrial control, telemedicine and remote driving),9 thThe class is remote control class flow (control instruction class flow in industrial control, telemedicine and remote driving). They contain deterministic network traffic related demand information including bandwidth, jitter, latency, etc. Will be provided withThey are used forThe method is divided into two types of matrixes of deterministic traffic types and non-deterministic traffic matrixes according to different types.
Step 1-2: modeling the formed flow matrix to obtain a flow matrix containing jitter and time delay information related information required by deterministic flow; the step 1-2 specifically comprises: traversing deterministic network information according to the classified deterministic traffic data in the step 1-1; the method comprises the steps of arranging end-to-end traffic in a network, and processing deterministic traffic and non-deterministic traffic into a traffic matrix form, wherein deterministic network topology information is represented by an undirected graph G (V, E), V represents a set of nodes, and V (N); e represents a set of links and | E | ═ L; and generating two traffic matrixes of deterministic traffic and non-deterministic traffic by the data set at each moment, wherein the value of each element represents the traffic demand sent between the corresponding OD pairs. The generated traffic matrix format is represented as follows:
wherein m isi,jRepresenting the flow demand from i to j.
Step 1-3: then, forecasting the deterministic traffic through an RNN (radio network) cyclic network algorithm to form a forecasting traffic matrix of the deterministic traffic with a relative time sequence; the steps 1-3 specifically comprise the following steps: and (2) generating a deterministic flow matrix according to the historical data set, constructing an RNN model, inputting the deterministic flow matrix with time correlation and deterministic flow demand data, automatically constructing the RNN model of the network flow and training, and after the training is finished, outputting the flow matrix of the predicted deterministic network in the next period of time after model calculation.
Step 2: and inputting the obtained deterministic network flow prediction data set with bandwidth, time delay and jitter requirements and topology basic information in the network into a network slicing algorithm based on reinforcement learning, and outputting bandwidth and port information required by the deterministic slicing to a network configuration module. Step 2 comprises the following substeps:
step 2-1: link bandwidth sizes in a deterministic network are collected by a network resource static collection module. The step 2-1 specifically comprises: static resources such as bandwidth and routing in a deterministic network are collected through a network static resource collection module, end-to-end link bandwidth information forms an end-to-end link bandwidth matrix, and the matrix is represented as follows:
wherein wi,jRepresenting the link bandwidth from i to j.
Step 2-2: and (3) inputting the data set of the deterministic network traffic matrix predicted by the RNN algorithm in the step (1) into a reinforcement learning network slicing algorithm, and generating network slicing module configuration parameters of a port number and a reserved bandwidth of the deterministic network resources which can be reserved. The step 2-2 specifically comprises: inputting the prediction data set of the deterministic network traffic matrix obtained in the step 1 and the static bandwidth resource data of the link obtained in the step 2-1 into a network slicing algorithm based on reinforcement learning, establishing a Markov decision model, searching an optimal strategy and maximizing the future expected reward. Deep reinforcement learning provides a universal algorithm framework for resource reservation of slices, and the universal algorithm framework comprises 3 basic elements of State space State, Action space Action and Reward return function Reward. For deterministic network scenarios, the following are defined:
1) the State represents a deterministic network State, includes three information, which are respectively a current deterministic slice resource reservation ratio, a link utilization rate in a deterministic network, and a resource guarantee rate of deterministic traffic, and can be specifically represented by the following 3 numerical values. Resource of sliceReserved ratio SsThe ratio of the deterministic slice to the whole system resource, and the resource utilization rate R in the linksIt refers to the ratio of the actual used link bandwidth to the total link bandwidth; the guarantee rate of the flow resource in the deterministic slice is divided into the synthesis of three indexes, namely a time delay guarantee DsJitter assurance JsBandwidth guarantee Ws. Resource guarantee rate AsIs a comprehensive expression of three indexes, and a State set is defined as S for the inside of a deterministic networks,Rs,As]
2) Action, representing the set of actions performed. The DRL will perform state acquisition and then select and execute an action according to a greedy algorithm. In a deterministic network, the action is to dynamically adjust the system duty cycle of the bandwidth resources in the link. And performing the increment allocation and the decrement allocation of the deterministic traffic link bandwidth on the original link bandwidth allocation.
3) Reward, which represents Reward feedback by environment interaction, rewards being performed according to executed actions, and in a deterministic network scenario, Reward is related to resource guarantee rate of deterministic traffic, defined herein as:
As＝αWs+βJs+γDs
assume that the current policy is expressed as
While
If it is the current reward function, then the current reward function is:
the optimal equation for the Q value can be expressed as:
where γ is the attenuation factor of the Markov process, so the decision function is defined as the difference of the actions of this state to transition to the next bandwidth reservation state, P is the probability of the state transition, assuming the next action as AtThen the decision function is:
by the above definition, a reward of maximizing future expectations of deterministic network slices can be made. And obtaining the occupation ratio of the reserved bandwidth slice to the whole link, and obtaining the reserved port number of the deterministic network resource and the network slice data of the reserved bandwidth.
Step 2-3: and reserving resources on the space bandwidth of the obtained configuration parameters in a network slice configuration module of the transmission module to form an initial network slice. The step 2-3 specifically comprises the following steps: the method comprises the steps that reserved data of a deterministic network slice generated by reinforcement learning is configured into a deterministic network through a network slice configuration module of a network transmission module, the bandwidth of a link is limited through a queue mechanism in a deterministic switch, the link bandwidth of the deterministic network and the link bandwidth of a non-deterministic network are isolated in a virtualization mode, and the bandwidths of the deterministic network and the non-deterministic network are not interfered with each other.
And step 3: and a bandwidth scheduling algorithm strategy of a time slot layer in a deterministic network slice configured by a network transmission module is used for performing a resource scheduling algorithm in the deterministic slice of the time slot layer, so that network congestion queuing and resource robbery generated when a plurality of deterministic data streams simultaneously reach an end node are reduced in a time dimension. Step 3 comprises the following substeps:
step 3-1: step 2 has generated two virtual sub-networks of deterministic network slices and non-deterministic network slices by configuration of the deterministic network, for real-time deterministic network traffic sum by the network status measurement moduleThey are used forExtracting and counting the type, time delay and jitter of the received signals; the step 3-1 specifically comprises:the state measurement in the deterministic network slice is carried out by an in-band measurement method in a network measurement module, the category classification of the deterministic traffic within 5 seconds of the period and the service requirements and quality such as time delay, bandwidth, jitter and the like required by the deterministic traffic within the period are extracted, and modeling is carried out, wherein different types of deterministic traffic are divided into different deterministic traffic matrixes.
Step 3-2: according to different types of the deterministic traffic, quantizing the bandwidth in the deterministic network slice into time slots, dividing the time slots in the deterministic network for the flexibly entered deterministic traffic, and performing resource scheduling on the bandwidth in the deterministic slice by using a time slot algorithm. The step 3-2 specifically comprises the following steps: because the types and the time of arrival of deterministic traffic are different, when bandwidth allocation of different deterministic services is performed in a deterministic slice, bandwidth resources can be quantized into time slots through the types of deterministic streams and indexes such as required bandwidth, time delay, jitter and the like which are achieved within 5s, wherein the total bandwidth resources in the deterministic slice are expressed as WS, a period is expressed as T, and when the deterministic stream is divided into N time slots, the corresponding bandwidth granularity of each time slot in the period T is
bw＝WS/N
The dispatching algorithm is used for carrying out preferential time slot distribution on the service with less time delay requirement, if the required time slots with higher priority in the deterministic flow are n, the bandwidth resources distributed in the period T in the deterministic network are the
BW1＝bw*n
Step 3-3: and adjusting the injection time of the scheduling flow in the network transmission module according to the result of the time slot algorithm division, thereby realizing the resource scheduling algorithm in the deterministic network slice based on the time slot. The step 3-3 specifically comprises the following steps: the strategy of the reserved time slot of each type of deterministic stream in the deterministic slice is obtained through the step 3-2, the injection time of various different deterministic type flows is adjusted in the network transmission module according to the strategy, the flexibility in the deterministic slice is guaranteed, and the resource scheduling algorithm in the deterministic network slice based on the time slot in the deterministic network is realized.
And 4, step 4: and (3) according to the link load condition and the statistic condition of the deterministic flow in the network measured by the network measurement module, regenerating the slicing strategy by using a method of designing a threshold, adjusting and generating the network slices, and repeating the steps of the step (1) to the step (4). Step 4 comprises the following substeps:
step 4-1: and performing state monitoring on the deterministic traffic in a deterministic network dynamic measurement module. The step 4-1 specifically comprises: and carrying out strategies and calculations on the utilization rate of the link of the deterministic network slice and the overall network state, the utilization rate of the deterministic network slice and the bandwidth satisfaction rate of the deterministic traffic through the deterministic network dynamic measurement module. And analyzing that the link utilization rate is VL, the deterministic network slice utilization rate is DL, the deterministic traffic bandwidth satisfaction rate is WL, and the non-deterministic traffic bandwidth satisfaction rate is UL.
Step 4-2: and (3) processing the network state data monitored in the step (4-1), analyzing the network state condition, and when the bandwidth, time delay and jitter average service guarantee rate of the deterministic traffic is less than a threshold value of 0.8, re-dividing the network slices and repeating the steps (1) to (3). The step 4-2 specifically comprises the following steps: the link utilization rate VL, the deterministic network slice utilization rate DL, the deterministic traffic bandwidth satisfaction rate WL, the non-deterministic traffic bandwidth satisfaction rate UL are obtained through the step 4-1, and the gain in the deterministic network is defined as:
since guaranteed is mainly the bandwidth of the deterministic network, it will be
The slice guarantee threshold K immediately after the generation of the slice is calculated with β set to 0.8 and 0.2. If Value in the subsequent time period T<If the number of times of K exceeds 30%, indicating that the slice needs to be adjusted, the slice regeneration is started, and the steps 1 to 3 are repeated.
Finally, it should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (9)
1. A network slice generation and dynamic configuration system facing to a deterministic network is characterized by comprising an information acquisition module, a software control module and a network transmission module; wherein the content of the first and second substances,
the information acquisition module is used for acquiring the information of the network transmission module and outputting the flow information in the deterministic network to the software control module;
the software control module is used for determinacy network slice prediction, construction, scheduling and adjustment, and outputting information to the network transmission module;
the output end of the network transmission module is connected with the information acquisition module and the underlying network topology and is used for issuing a deterministic network flow table and configuring deterministic network slices.
2. The deterministic network-oriented network slice generation and dynamic configuration system of claim 1, wherein the information collection module comprises a deterministic network dynamic measurement module and a deterministic network static measurement module; wherein the content of the first and second substances,
the deterministic network dynamic measurement module is used for measuring the link load state and the network flow state in the network to obtain the traffic in the deterministic network represented in the form of a flow matrix and bandwidth, time delay and jitter information required by the deterministic traffic;
and the deterministic network static measurement module is used for measuring static information in the network, wherein the static information comprises router connection condition, port condition and link bandwidth information.
3. The deterministic network-oriented network slice generation and dynamic configuration system of claim 2, wherein the software control module comprises a deterministic network slice prediction module, a deterministic network slice construction module, a deterministic network slice scheduling module, a deterministic network slice adjustment template; wherein the content of the first and second substances,
the deterministic network slice prediction module is used for predicting the deterministic network flow of a period of time in the future by an RNN (radio network) cyclic network method;
the deterministic network slice construction module is used for reserving the bandwidth of the link by a deep reinforcement learning network slice method to output the occupation ratio of the deterministic network slice to the link;
the deterministic network slice scheduling module is used for scheduling resources in the deterministic network slice on the basis of time slots through required bandwidth, time delay and jitter of real-time deterministic traffic in the network output by the measuring module;
and the deterministic network slice adjusting template is used for outputting the link real-time state through the network dynamic measuring module, and carrying out re-deterministic network slice construction if the load of the deterministic network exceeds a set threshold value.
4. The deterministic network-oriented network slice generation and dynamic configuration system of claim 3, wherein the network transport module comprises a deterministic network flow table issuing module and a deterministic network slice configuration module, wherein,
the deterministic network flow table issuing module is used for configuring a port and issuing a flow table to a network layer through flow table information;
and the deterministic network slice configuration module is used for performing link bandwidth allocation and configuration of the deterministic switch through the slice information output by the network slice module.
5. The network slice generation and dynamic configuration method for the deterministic network is characterized by comprising the following steps:
step 1: collecting a deterministic flow data set, generating a deterministic flow matrix and needed jitter and time delay information, inputting the obtained deterministic flow matrix and related information into a depth model according to a time sequence to perform flow prediction, and performing deterministic network flow prediction;
step 2: inputting the obtained deterministic network flow prediction data set with bandwidth, time delay and jitter requirements and topology basic information in a network into a network slicing algorithm based on reinforcement learning to form bandwidth and port information required by a deterministic slice, and configuring the deterministic network slice according to the bandwidth and port information required by the deterministic slice;
and step 3: the method comprises the steps that a bandwidth scheduling algorithm strategy of a time slot level is applied to a deterministic network slice, resource scheduling in the deterministic slice of the time slot level is carried out, and network congestion queuing and resource robbing generated when a plurality of deterministic data streams reach an end node at the same time are reduced in a time dimension;
and 4, step 4: calculating network profit according to link bandwidth, topology and deterministic traffic information in a network, returning to the step 1 if the network profit does not meet a certain design threshold, and carrying out regeneration and dynamic configuration of a slicing strategy; otherwise, collection of link bandwidth, topology and deterministic traffic information in the network is maintained.
6. The deterministic network-oriented network slice generation and dynamic configuration method of claim 5, wherein the step 1 comprises the following sub-steps:
step 1-1: collecting historical traffic data in a network by using output data of a data acquisition module, and classifying the historical traffic data according to different deterministic service requirements to form a deterministic network traffic matrix and a non-deterministic network traffic matrix;
step 1-2: modeling the formed flow matrix to obtain a flow matrix containing jitter and time delay information related information required by deterministic flow;
step 1-3: and then, forecasting the deterministic traffic through an RNN (radio network) cyclic network algorithm to form a forecasting traffic matrix of the deterministic traffic with relative time sequence.
7. The deterministic network-oriented network slice generation and dynamic configuration method of claim 6, wherein the step 2 comprises the sub-steps of:
step 2-1: collecting link bandwidth sizes in a deterministic network by a network resource static collection module;
step 2-2: inputting the data set of the deterministic network traffic matrix predicted by the RNN algorithm in the step 1 into a reinforcement learning network slicing algorithm to generate network slicing module configuration parameters of a port number and a reserved bandwidth of the deterministic network resources which can be reserved;
step 2-3: and reserving resources on the space bandwidth of the obtained configuration parameters in a network slice configuration module of the transmission module to form an initial network slice.
8. The deterministic network-oriented network slice generation and dynamic configuration method of claim 7, wherein the step 3 comprises the sub-steps of:
step 3-1: step 2, two virtual sub-networks of a deterministic network slice and a non-deterministic network slice are generated by configuring a deterministic network, and real-time deterministic network flow and types, time delay and jitter of the real-time deterministic network flow are extracted and counted by a network state measuring module;
step 3-2: quantizing the bandwidth in the deterministic network slice into time slots according to different types of the deterministic traffic, dividing the time slots in the deterministic network for the flexibly entered deterministic traffic, and performing resource scheduling on the bandwidth in the deterministic slice by using a time slot algorithm;
step 3-3: and adjusting the injection time of the scheduling flow in the network transmission module according to the result of the time slot algorithm division, thereby realizing the resource scheduling algorithm in the deterministic network slice based on the time slot.
9. The deterministic network-oriented network slice generation and dynamic configuration method of claim 8, wherein the step 4 comprises the sub-steps of:
step 4-1: performing state monitoring on the deterministic traffic in a deterministic network dynamic measurement module;
step 4-2: and (4) processing the network state data monitored in the step (4-1), analyzing the network state condition, and regenerating and configuring a deterministic network slice when the bandwidth, time delay and jitter average service guarantee rate of the deterministic traffic is less than a design threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111424669.XA CN114268537B (en) | 2021-11-26 | 2021-11-26 | Deterministic network-oriented network slice generation and dynamic configuration system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111424669.XA CN114268537B (en) | 2021-11-26 | 2021-11-26 | Deterministic network-oriented network slice generation and dynamic configuration system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114268537A true CN114268537A (en) | 2022-04-01 |
| CN114268537B CN114268537B (en) | 2023-12-22 |
Family
ID=80825645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111424669.XA Active CN114268537B (en) | 2021-11-26 | 2021-11-26 | Deterministic network-oriented network slice generation and dynamic configuration system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114268537B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115632925A (en) * | 2022-12-26 | 2023-01-20 | 北京交通大学 | Time-certainty fusion network architecture and data communication method |
| CN115955403A (en) * | 2022-12-06 | 2023-04-11 | 煤炭科学技术研究院有限公司 | Mining network slicing method and system |
| CN115987814A (en) * | 2022-12-23 | 2023-04-18 | 众芯汉创（北京）科技有限公司 | Deterministic network computing system for 5GURLLC scene delay |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107659419A (en) * | 2016-07-25 | 2018-02-02 | 华为技术有限公司 | Network dicing method and system |
| CN107743100A (en) * | 2017-09-30 | 2018-02-27 | 重庆邮电大学 | A kind of online adaptive network section virtual resource allocation method based on traffic forecast |
| CN109600259A (en) * | 2018-12-11 | 2019-04-09 | 浙江工商大学 | A kind of real-time Transmission mechanism based on software definable |
| CN110048869A (en) * | 2018-01-16 | 2019-07-23 | 中国科学院沈阳自动化研究所 | Resource allocation methods and system towards industrial time-sensitive software defined network |
| CN110519783A (en) * | 2019-09-26 | 2019-11-29 | 东华大学 | 5G network based on enhancing study is sliced resource allocation methods |
| EP3684137A1 (en) * | 2019-01-21 | 2020-07-22 | Nokia Solutions and Networks GmbH & Co. KG | Providing connectivity service to multiple tsn domains by a single 3gpp network |
| CN111866953A (en) * | 2019-04-26 | 2020-10-30 | ***通信有限公司研究院 | Network resource allocation method, device and storage medium |
| CN112511329A (en) * | 2020-06-12 | 2021-03-16 | 中兴通讯股份有限公司 | Information notification method and device and readable medium |
| US20210243641A1 (en) * | 2018-08-14 | 2021-08-05 | Huawei Technologies Co., Ltd. | Time-aware quality-of-service in communication systems |
-
2021
- 2021-11-26 CN CN202111424669.XA patent/CN114268537B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107659419A (en) * | 2016-07-25 | 2018-02-02 | 华为技术有限公司 | Network dicing method and system |
| CN107743100A (en) * | 2017-09-30 | 2018-02-27 | 重庆邮电大学 | A kind of online adaptive network section virtual resource allocation method based on traffic forecast |
| CN110048869A (en) * | 2018-01-16 | 2019-07-23 | 中国科学院沈阳自动化研究所 | Resource allocation methods and system towards industrial time-sensitive software defined network |
| US20210243641A1 (en) * | 2018-08-14 | 2021-08-05 | Huawei Technologies Co., Ltd. | Time-aware quality-of-service in communication systems |
| CN109600259A (en) * | 2018-12-11 | 2019-04-09 | 浙江工商大学 | A kind of real-time Transmission mechanism based on software definable |
| EP3684137A1 (en) * | 2019-01-21 | 2020-07-22 | Nokia Solutions and Networks GmbH & Co. KG | Providing connectivity service to multiple tsn domains by a single 3gpp network |
| CN111866953A (en) * | 2019-04-26 | 2020-10-30 | ***通信有限公司研究院 | Network resource allocation method, device and storage medium |
| CN110519783A (en) * | 2019-09-26 | 2019-11-29 | 东华大学 | 5G network based on enhancing study is sliced resource allocation methods |
| CN112511329A (en) * | 2020-06-12 | 2021-03-16 | 中兴通讯股份有限公司 | Information notification method and device and readable medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115955403A (en) * | 2022-12-06 | 2023-04-11 | 煤炭科学技术研究院有限公司 | Mining network slicing method and system |
| CN115987814A (en) * | 2022-12-23 | 2023-04-18 | 众芯汉创（北京）科技有限公司 | Deterministic network computing system for 5GURLLC scene delay |
| CN115987814B (en) * | 2022-12-23 | 2023-10-31 | 众芯汉创（北京）科技有限公司 | Deterministic network computing system for 5GURLLC scene delay |
| CN115632925A (en) * | 2022-12-26 | 2023-01-20 | 北京交通大学 | Time-certainty fusion network architecture and data communication method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114268537B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114268537B (en) | Deterministic network-oriented network slice generation and dynamic configuration system and method | |
| Yu et al. | Traffic statistics and performance evaluation in optical burst switched networks | |
| RU2677373C1 (en) | Fractal telecommunication traffic transmission quality increasing method | |
| Buyakar et al. | Resource allocation with admission control for GBR and delay QoS in 5G network slices | |
| CN114286413A (en) | TSN network combined routing and stream distribution method and related equipment | |
| CN112733303B (en) | Multi-strategy industrial TSN shaper modeling method based on deterministic network algorithm | |
| US20220104127A1 (en) | Method and apparatus for power management in a wireless communication system | |
| CN115766884A (en) | Computing task processing method, device, equipment and medium | |
| Bonald et al. | A queueing analysis of data networks | |
| Chong et al. | Probabilistic burstiness-curve-based connection control for real-time multimedia services in ATM networks | |
| KR20120055947A (en) | Method and apparatus for providing Susbscriber-aware per flow | |
| RU2742038C1 (en) | Method for dynamic quasioptimal performance distribution when processing real-time fractal traffic in systems with failures | |
| CN114257554A (en) | Scheduling method for improving TSN (traffic service network) BE (BE) stream bandwidth utilization rate | |
| KR100818303B1 (en) | Method for predicting traffic characteristics and traffic estimation devices for the wired and wireless networks | |
| Kozlovskiy et al. | DEVELOPMENT OF A MODIFIED METHOD OF NETWORK TRAFFIC FORMING | |
| Romanchuk et al. | Method of multiservice infrastructure decomposition with network resource slicing for IoT | |
| CN113727389A (en) | Method, equipment and system for determining bandwidth of transmission service flow | |
| Arfaoui et al. | Flexible network slicing assisted 5G for video streaming with effective and efficient isolation | |
| CN116095175B (en) | Data flow scheduling method and device for grid edge computing system | |
| Kostiv et al. | Metaheuristics in cloud platform traffic engineering | |
| CN115190082B (en) | Traffic flow scheduling method and device of TSN (traffic stream network) | |
| RU2804500C1 (en) | Method for reserving bandwidth for aggregated fractal traffic with adaptation to the current load | |
| Ðue et al. | A model of traffic prediction based admission control in OBS nodes | |
| Lozhkovskyi et al. | UDC 621. 391 method for approximating the distribution function of the states in the single-channel system with a self-similar traffic | |
| Fang et al. | Token regulated credit based shaper for time sensitive networks |
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 |