CN114826937B - Flow sensing method based on size time scale under world integration network - Google Patents

Flow sensing method based on size time scale under world integration network Download PDF

Info

Publication number
CN114826937B
CN114826937B CN202210406109.XA CN202210406109A CN114826937B CN 114826937 B CN114826937 B CN 114826937B CN 202210406109 A CN202210406109 A CN 202210406109A CN 114826937 B CN114826937 B CN 114826937B
Authority
CN
China
Prior art keywords
flow
node
transfer
time scale
resource
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210406109.XA
Other languages
Chinese (zh)
Other versions
CN114826937A (en
Inventor
曲桦
袁晓东
赵季红
解朋飞
魏锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
Original Assignee
Xian Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University filed Critical Xian Jiaotong University
Priority to CN202210406109.XA priority Critical patent/CN114826937B/en
Publication of CN114826937A publication Critical patent/CN114826937A/en
Application granted granted Critical
Publication of CN114826937B publication Critical patent/CN114826937B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/14—Relay systems
    • H04B7/15—Active relay systems
    • H04B7/185—Space-based or airborne stations; Stations for satellite systems
    • H04B7/1853—Satellite systems for providing telephony service to a mobile station, i.e. mobile satellite service
    • H04B7/18539—Arrangements for managing radio, resources, i.e. for establishing or releasing a connection
    • H04B7/18541—Arrangements for managing radio, resources, i.e. for establishing or releasing a connection for handover of resources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/50—Queue scheduling
    • H04L47/56—Queue scheduling implementing delay-aware scheduling
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Abstract

The invention discloses a flow sensing method based on a size time scale under a space-earth integration network, which aims at the fact that an space-earth integration architecture provided by a space-earth integration network environment can sense and collect network resource nodes in an area and process flow information, can adapt to the characteristics of the space-earth integration network to predict the flow in the area under the large time scale, and can judge whether resources in the area can meet resource requirements corresponding to the predicted flow. The resource node overload condition caused by the burstiness of the traffic on the small time scale can be reduced by transferring the delay-sensitive type cross-node traffic on the small time scale, and the resource utilization rate of idle nodes can be improved by performing queue caching and traffic transfer on the delay-tolerant traffic.

Description

Flow sensing method based on size time scale under world integration network
Technical Field
The invention belongs to the field of a space-earth integration information network, and particularly relates to a flow sensing method based on a size time scale under a space-earth integration network.
Background
In recent years, as an emerging network architecture integrating satellite and terrestrial communication systems, a world convergence network has gained extensive attention in academia and industry, and is an important component of national competitive strength and viability, which relates to national economy and national security development strategy. Owing to the advantages of wide coverage, high throughput, strong robustness and the like, the world fusion network can be applied to a plurality of actual fields such as earth observation and mapping, intelligent traffic systems, military tasks, homeland security, disaster rescue and the like. Satellites with high throughput are capable of providing seamless wireless access services worldwide, with densely deployed terrestrial network infrastructure supporting high-speed data access. The convergence of the space-based and ground-based networks can bring immeasurable benefits to future 6G wireless communication systems, providing more applications and services.
For the world convergence network, due to the characteristics of isomerism, self-organization, dynamic property and the like of the world convergence network, the convergence network brings significant benefits for various services and applications, and simultaneously faces many challenges such as routing, resource allocation, power control, end-to-end service quality requirements and the like. The fusion of the space-based network and the foundation network can bring about the increase of service types and quantity, the traditional flow sensing is carried out on a large time scale, such as tens of minutes, the network flow in the area is predicted and sensed under the large time scale, and the resource demand corresponding to the flow is met by the resource scheduling through the prediction result, however, the flow prediction sensing only solves the flow change of the large time scale, cannot cope with the fine granularity flow change of the small time scale under a large number of service scenes in the space-based fusion network, such as seconds or hundreds of milliseconds, and the flow under the small time scale has burstiness, so that the overload condition occurs to partial nodes in the area, thereby influencing the service quality in the whole area.
At present, the research on the flow sensing of the heaven-earth fusion network is basically carried out under a large time scale, the flow change under a small time scale is rarely considered, the traditional flow prediction algorithm is only aimed at a single network, either a satellite network or a ground network, and the flow prediction research on the heaven-earth fusion network is less. The general flow prediction is of two types, namely linear and nonlinear, wherein the linear needs to manually set parameters to fit data by experience, the application range is small, and the actual network flow has the characteristics of nonlinearity, periodicity, burstiness, autonomy and the like, so that the application range of the nonlinear flow prediction is large, however, the traditional flow prediction is carried out in a single network, and the characteristics of an space-based network and a foundation network are not considered jointly, so that the method is not suitable for carrying out flow prediction in a space-earth fusion network.
The traditional flow sensing processing is only aimed at the condition of a large time scale, the flow change of a small time scale is rarely considered, and the flow change is generally difficult to predict, so that the flow change under the small time scale is always ignored, the sudden change of the flow can lead to different results of nodes at different times, the overload can cause congestion when the flow mutation is in a peak value, so that the nodes generate larger service delay, the service quality of the nodes is reduced, or the node is idle when the flow mutation is in a valley bottom, so that the waste of node resources is caused. Therefore, how to solve the sudden change of the flow under a small time scale is very important for node flow balance and reasonable resource utilization in the area.
Disclosure of Invention
The invention aims to overcome the defects, and provides a flow sensing method based on a large time scale and a small time scale under a space-earth integration network, aiming at the characteristics of multidimensional resources, resource dynamics and small time scale flow burstiness of the space-earth integration network, a Markov-based flow prediction method under a large time scale is provided, characteristics of space-based nodes and foundation nodes are considered, flow in an area is predicted under the large time scale to judge whether the resources in the area can meet flow requirements, then flow transfer is carried out on delay sensitive type according to the burstiness of the flow and the characteristics of the considered flow under the small time scale, and delay tolerant type put into a queue for caching and flow transfer.
In order to achieve the above object, the present invention comprises the steps of:
s1, modeling a world integration network to obtain a satellite ground node resource pool;
s2, predicting the arrival of the flow in the area;
s3, judging whether satellite ground resources in a large time scale meet the resource requirements of the flow in the area according to the prediction result;
s4, determining precondition parameters for carrying out small time scale flow transfer;
s5, carrying out flow transfer according to the flow size, the type and the resource state;
and S6, carrying out flow equalization and resource state evaluation of the nodes according to the result after the flow transfer.
The specific method of S1 is as follows:
the satellite and ground nodes are virtualized, the dynamic property of the satellite nodes is shielded, and the satellite and ground nodes are covered by a group of invariable virtual satellite nodes and ground nodes in a geographic area in a time slice, so that a satellite and ground node resource pool is obtained.
S2, a specific method for predicting the arrival of the flow in the area is as follows:
predicting in a large time scale according to historical data and flow of satellite ground flow in an area periodically, obtaining a frequency transfer matrix according to a state set and the historical flow data, obtaining the state transfer matrix according to the frequency transfer matrix, further establishing a Markov transfer chain, and predicting the flow at the next moment by analyzing the state transfer.
In S3, the method for judging whether the satellite ground resources in the large time scale meet the resource requirements of the traffic in the area according to the prediction result is as follows:
A long ＝C long ,S long ,T long }
wherein ,Along For flow H at large time scale ′ Corresponding resource requirements need to be satisfied:
Figure BDA0003602219750000031
Figure BDA0003602219750000032
wherein ,
Figure BDA0003602219750000033
for the total amount of resources within a large time scale, +.>
Figure BDA0003602219750000034
Is the amount of used resources.
In S4, precondition parameters for small time scale flow transfer are as follows:
N 0 ＝βN
wherein ,N0 In order to accommodate the node which can accept the flow transfer, N is the total node number in the area, and beta is the number used for adjusting the accommodating node.
S5, performing traffic transfer including delay sensitive DS and delay tolerant DT;
under the condition of the same flow, the node firstly meets the resource requirement of the delay-sensitive DS, the residual resources change along with the dynamic resource requirement of the delay-sensitive DS, and the resource requirement of the delay-tolerant DT is dynamically supplied through the residual resources.
The traffic transfer of the delay-sensitive DS is based on a threshold T i To determine the threshold T i Determined by the amount of resources of the node:
T i ＝γ·RES t ，
Figure BDA0003602219750000041
wherein ,Fi RES for the current traffic of node i on a small time scale t Is a ground node resource pool;
the flow rate is transferred when the flow rate exceeds the threshold value, and the transferred flow rate is F ij ,j∈N 0 To accommodate a node, the traffic of node j after transfer is:
Figure BDA0003602219750000042
wherein ni=n-No, F j The original flow of the accommodating node is obtained;
for the delay tolerant DT related to the current node's resource amount and delay sensitive DS, different kinds of delay tolerant DT have different resource amount requirements recorded as
Figure BDA0003602219750000043
The node i allocates resources to the delay tolerant DT with k types in the time slot t, and the unfinished delay tolerant DT is replaced in the queue Q (t), and the length of the queue should be controlled because the delay tolerant DT also has a delay requirement:
Figure BDA0003602219750000044
wherein ,si The processing speed of the node i is 0.ltoreq.s i ≤1，
Figure BDA0003602219750000045
For handling an existing traffic in the queue at time slot t,/>
Figure BDA0003602219750000046
Delay tolerant DT traffic size of class k for arrival at time slot t;
when the average processing speed of the node is smaller than the average flow arrival rate, performing flow transfer, wherein the flow of the node j after transfer is as follows:
Figure BDA0003602219750000047
wherein the diverted flow is
Figure BDA0003602219750000048
i, j e N is a node with the ability to accept traffic transfer.
Through the flow transfer of the delay sensitive DS and the queue buffer and the flow transfer of the delay tolerant DT, the method reduces the flow overload quantity of nodes in the area, improves the resource utilization of idle nodes, reduces the overload ratio of the nodes in the area, and has the following formula:
Figure BDA0003602219750000051
wherein ,Rover Is a region ofIntra-domain node overload ratio, N over The number of the overloaded nodes;
for delay tolerant DT to ensure queue stability, the following formula is given:
Q i (t)≤Q T
wherein ,QT And determining whether the DT performs the flow transfer across the nodes or not according to the threshold value of the queue length and the node processing speed and the flow arrival speed.
Compared with the prior art, the space-earth fusion architecture provided by the invention aiming at the space-earth fusion network environment can sense and collect network resource nodes in an area and process flow information, can adapt to the characteristics of the space-earth fusion network to predict the flow in the area under a large time scale, and can judge whether resources in the area can meet the resource requirements corresponding to the predicted flow. The resource node overload condition caused by the burstiness of the traffic on the small time scale can be reduced by transferring the delay-sensitive type cross-node traffic on the small time scale, and the resource utilization rate of idle nodes can be improved by performing queue caching and traffic transfer on the delay-tolerant traffic.
Drawings
FIG. 1 is a diagram of a network architecture of the present invention;
FIG. 2 is a flow chart of flow prediction in a region at a large time scale in accordance with the present invention;
FIG. 3 is a flow chart of a small time scale flow transfer in accordance with the present invention;
FIG. 4 is a schematic diagram of peak clipping and valley filling for flow transfer in the present invention;
FIG. 5 is a graph of node overload ratios and resource utilization before and after traffic transfer in accordance with the present invention;
Detailed Description
The invention is further described below with reference to the accompanying drawings.
According to the SDN-based heaven-earth fusion network architecture, a flow processing module in the architecture performs large-time-scale flow prediction, a flow of flow prediction is shown in a graph 2, a small-time-scale cross-node flow transfer flow is shown in a graph 3, a flow equilibrium state of nodes in a region after flow transfer is finally obtained, and peak clipping and valley filling of flow transfer are shown in a graph 4.
The method specifically comprises the following steps:
step 1, constructing an heaven-earth integrated architecture, and obtaining a virtualized multidimensional resource pool, wherein the constructed heaven-earth integrated network architecture is provided with a control layer, a flow processing layer and a resource layer, as shown in fig. 1, wherein:
the control layer is mainly based on controllers of the SDN to obtain information of the network and to control and manage the network,
the traffic handling layer is mainly responsible for large time scale traffic prediction and small time scale traffic diversion,
the resource layer virtualizes the space base and the foundation nodes, abstracts multidimensional resources, shields the dynamic property of satellite nodes, obtains a satellite ground node resource pool,
the geographical area within the time slice can be seen as covered by a set of unchanged virtual satellite nodes and ground nodes, the resulting satellite and ground node resource pool RES t ＝{C t ,S t ,T t },0<t is less than or equal to Th, wherein C t For computing resources, S t To store resources, T t For transmitting a resource, the resource has a survival time of 0<t.ltoreq.Th indicates that the node is within the geographical area.
Step 2, predicting the flow at the next moment, predicting the arrival of the flow in the area according to the characteristic of periodicity of the flow in the world integration network, and predicting the arrival of the flow in the area according to the historical data of the satellite ground flow in the area and the characteristic of periodicity of the flow, wherein the prediction under a large time scale is shown in fig. 2, the historical flow data is H, a corresponding state set S= {1, 2..s } is divided, and a frequency transfer matrix f is obtained according to the state set and the historical flow data ij Then, a state transition matrix P(s) =p is obtained ij (s)，p ij (s)＝P{x s+1 ＝j|x s =i } represents the probability of j over 1 step with time s in state i, where p ij (s)≥0，∑ j∈s p ij (s) =1, thereby establishing a markov transfer chain { x } n N=1, 2..k }, and the flow H at the next time is predicted by analyzing the state transition ′ If (if)
Figure BDA0003602219750000061
The prediction result is considered to be authentic, otherwise the historical data average value +.>
Figure BDA0003602219750000062
Step 3, determining whether the resource requirement is met according to the prediction result, judging whether the satellite ground resource meets the resource requirement of the flow in the area in a large time scale, determining whether the existing resource quantity meets the resource requirement corresponding to the flow according to the flow prediction result, wherein the steps are as follows:
A long ＝C long ,S long ,T long }
wherein ,Along For flow H at large time scale ′ Corresponding resource requirements need to be met
Figure BDA0003602219750000071
Figure BDA0003602219750000072
wherein ,
Figure BDA0003602219750000073
for the total amount of resources within a large time scale, +.>
Figure BDA0003602219750000074
Is the amount of used resources.
Step 4, determining precondition parameters for carrying out small time scale flow transfer, wherein in consideration of the complexity of flow transfer under the small time scale, partial nodes are required to be set to have the capacity of accepting the flow transfer, and the parameters N are as follows 0 =βn, where N 0 For the node of the accommodating node acceptable traffic transfer, N is the total node number in the area, the parameter beta is used for adjusting the number of the accommodating nodes, and for the delay tolerant traffic, the type can be usedA nearby idle node is selected as an accommodating node because a certain delay is tolerated;
step 5, implementing the traffic transfer, and performing the traffic transfer according to the traffic size, type and resource state, as shown in fig. 3, the small time scale cross-node traffic transfer considers two different scenarios: the delay-sensitive DS and the delay-tolerant DT have the same traffic, and a smaller service delay results in a larger resource demand, so that the node should ensure a lower overload level, so that the resource demand of the delay-sensitive DS is satisfied first, the remaining resources change with the dynamic resource demand of the delay-sensitive DS, and the resource demand of the delay-tolerant DT is dynamically supplied by the remaining resources.
The flow transfer to the delay-sensitive DS is based on a certain threshold T i To determine T i Determined by the resource amount of the node
T i ＝γ·RES t ，
Figure BDA0003602219750000075
wherein ,Fi For the current traffic of node i on a small time scale,
the flow rate is transferred when the flow rate exceeds the threshold value, and the transferred flow rate is F ij ,j∈N 0 To accommodate a node, the traffic of node j after transfer is
Figure BDA0003602219750000081
Wherein ni=n-No, F j The original flow of the accommodating node is obtained;
for the delay tolerant DT related to the current node's resource amount and delay sensitive DS, different kinds of delay tolerant DT have different resource amount requirements recorded as
Figure BDA0003602219750000082
Indicating the resources allocated by node i to delay tolerant DT of class k at time slot t,the unfinished delay tolerant DT can be replaced in the queue Q (t), and the length of the queue should be controlled because the delay tolerant DT also has a certain delay requirement:
Figure BDA0003602219750000083
wherein ,si The processing speed of the node i is 0.ltoreq.s i ≤1，
Figure BDA0003602219750000084
For handling an existing traffic in the queue at time slot t,/>
Figure BDA0003602219750000085
For a delay tolerant DT traffic size of class k coming at time slot t,
when the average processing speed of the node is smaller than the average traffic arrival rate, the traffic transfer is performed because the queue is too long and unstable and the delay requirement cannot be met, and the traffic of the node j after the transfer is as follows:
Figure BDA0003602219750000086
wherein the diverted flow is
Figure BDA0003602219750000087
i, j e N is a node with the ability to accept traffic transfer.
Step 6, evaluating the effect of the traffic transfer, carrying out traffic balance and resource state evaluation of the nodes according to the result of the traffic transfer, and reducing the traffic overload quantity of the nodes in the area, improving the resource utilization of the idle nodes and reducing the overload ratio of the nodes in the area by carrying out traffic transfer on the delay sensitive DS and queue buffer and traffic transfer of the delay tolerant DT, wherein the method comprises the following formula:
Figure BDA0003602219750000088
subjecttoN(1-β)≤ni<N，
Figure BDA0003602219750000089
i,j＝1,…,N；
wherein ,Rover N is the node overload ratio in the area over As the number of nodes to be overloaded,
the stability of the queue to be guaranteed for the delay tolerant DT is given by the following formula
Q i (t)≤Q T ，
Figure BDA0003602219750000091
i,j＝1,…,N；
wherein ,QT The threshold value of the queue length is used for determining whether the delay tolerant DT performs the flow transfer across the nodes together with the node processing speed and the flow arrival speed.
Fig. 5 illustrates a node overload ratio and a resource utilization ratio diagram before and after traffic transfer, and it can be seen that the resource utilization ratio is very low when the overload ratio of the node is higher before traffic is not transferred, and the overload ratio of the node is greatly reduced to 8.4% after traffic transfer, so that the resource utilization ratio is improved to 92.1%, which illustrates that the invention can effectively reduce the resource node overload condition caused by traffic burstiness on a small time scale, and also improve the resource utilization ratio.

Claims (5)

1. The flow sensing method based on the size time scale under the world integration network is characterized by comprising the following steps of:
s1, modeling a world integration network to obtain a satellite ground node resource pool;
s2, predicting the arrival of the flow in the area;
s3, judging whether satellite ground resources in a large time scale meet the resource requirements of the flow in the area according to the prediction result;
s4, determining precondition parameters for carrying out small time scale flow transfer; precondition parameters for small time scale flow transfer are as follows:
N 0 ＝βN
wherein ,N0 The node is an accommodating node, namely the node which can accept flow transfer, N is the total node number in the area, and beta is the number used for adjusting the accommodating node;
s5, carrying out flow transfer according to the flow size, the type and the resource state; performing traffic transfer including delay sensitive DS and delay tolerant DT;
under the condition of the same flow, the node firstly meets the resource requirement of the delay sensitive DS, the residual resources change along with the dynamic resource requirement of the delay sensitive DS, and the resource requirement of the delay tolerant DT is dynamically supplied through the residual resources;
the traffic transfer of the delay-sensitive DS is based on a threshold T i To determine the threshold T i Determined by the amount of resources of the node:
T i ＝γ·RES t ，
Figure FDA0004171621820000011
wherein ,Fi RES for the current traffic of node i on a small time scale t Is a ground node resource pool;
the flow rate is transferred when the flow rate exceeds the threshold value, and the transferred flow rate is F ij ，j∈N 0 To accommodate a node, the traffic of node j after transfer is:
Figure FDA0004171621820000012
wherein ni=n-N 0 ，F j The original flow of the accommodating node is obtained;
traffic transfer for delay tolerant DT is related to the amount of resources of the current node and the resource requirements of the delay sensitive DS, heterogeneousClass delay tolerant DTs have different resource requirements recorded as
Figure FDA0004171621820000027
The node i allocates resources to the delay tolerant DT with k types in the time slot t, and the unfinished delay tolerant DT is cached in the queue Q (t), and the length of the queue should be controlled because the delay tolerant DT also has a delay requirement:
Figure FDA0004171621820000021
wherein ,si The processing speed of the node i is 0.ltoreq.s i ≤1，
Figure FDA0004171621820000022
To handle the existing traffic in the queue at time slot t,
Figure FDA0004171621820000023
the flow size of delay tolerant DT with K types coming in time slot t, K being the number of types of delay tolerant DT;
when the average processing speed of the node is smaller than the average flow arrival rate, performing flow transfer, wherein the flow of the node j after transfer is as follows:
Figure FDA0004171621820000024
wherein the diverted flow is
Figure FDA0004171621820000025
For a node with the capacity to accept traffic transfer, < >>
Figure FDA0004171621820000026
The original flow of the accommodating node is obtained;
and S6, carrying out flow equalization and resource state evaluation of the nodes according to the result after the flow transfer.
2. The flow sensing method based on a size time scale under a converged network according to claim 1, wherein the specific method of S1 is as follows:
the satellite and ground nodes are virtualized, the dynamic property of the satellite nodes is shielded, and the satellite and ground nodes are covered by a group of invariable virtual satellite nodes and ground nodes in a geographic area in a time slice, so that a satellite and ground node resource pool is obtained.
3. The flow sensing method based on the size time scale under the world convergence network according to claim 1, wherein in S2, the specific method for predicting the arrival of the flow in the area is as follows:
predicting in a large time scale according to historical data and flow of satellite ground flow in an area periodically, obtaining a frequency transfer matrix according to a state set and the historical flow data, obtaining the state transfer matrix according to the frequency transfer matrix, further establishing a Markov transfer chain, and predicting the flow at the next moment by analyzing the state transfer.
4. The flow sensing method based on the size time scale under the heaven-earth fusion network according to claim 1, wherein in S3, the method for judging whether the satellite ground resources in the large time scale meet the resource requirements of the flow in the area according to the prediction result is as follows:
A long ＝{C long ，S long ，T long }
wherein ,Along For the resource requirement corresponding to the flow H' under the large time scale, the following needs to be satisfied:
Figure FDA0004171621820000031
Figure FDA0004171621820000032
wherein ,
Figure FDA0004171621820000033
for the total amount of resources within a large time scale, +.>
Figure FDA0004171621820000034
Is the amount of used resources.
5. The flow sensing method based on the size time scale under the heaven-earth fusion network according to claim 1, wherein the flow overload quantity of nodes in an area is reduced, the resource utilization of idle nodes is improved, the overload ratio of the nodes in the area is reduced by the flow transfer of delay sensitive DS and the queue buffering and the flow transfer of delay tolerant DT, and the following formula is provided:
Figure FDA0004171621820000035
wherein ,Rover N is the node overload ratio in the area over The number of the overloaded nodes;
for delay tolerant DT to ensure queue stability, the following formula is given:
Q i (t)≤Q T
wherein ,QT And determining whether the DT performs the flow transfer across the nodes or not according to the threshold value of the queue length and the node processing speed and the flow arrival speed.
CN202210406109.XA 2022-04-18 2022-04-18 Flow sensing method based on size time scale under world integration network Active CN114826937B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210406109.XA CN114826937B (en) 2022-04-18 2022-04-18 Flow sensing method based on size time scale under world integration network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210406109.XA CN114826937B (en) 2022-04-18 2022-04-18 Flow sensing method based on size time scale under world integration network

Publications (2)

Publication Number Publication Date
CN114826937A CN114826937A (en) 2022-07-29
CN114826937B true CN114826937B (en) 2023-06-20

Family

ID=82537416

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210406109.XA Active CN114826937B (en) 2022-04-18 2022-04-18 Flow sensing method based on size time scale under world integration network

Country Status (1)

Country Link
CN (1) CN114826937B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111194045A (en) * 2019-12-28 2020-05-22 西安交通大学 Energy-saving method based on user group aggregation behavior model
WO2021174735A1 (en) * 2020-03-03 2021-09-10 中国科学院计算技术研究所 Dynamic resource scheduling method for guaranteeing latency slo of latency-sensitive application, and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111194045A (en) * 2019-12-28 2020-05-22 西安交通大学 Energy-saving method based on user group aggregation behavior model
WO2021174735A1 (en) * 2020-03-03 2021-09-10 中国科学院计算技术研究所 Dynamic resource scheduling method for guaranteeing latency slo of latency-sensitive application, and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
An SDN-Based Space-Air-Ground Integrated Network Architecture and Controller Deployment Strategy;Hua Qu等;《2020 IEEE 3rd International Conference on Computer and Communication Engineering Technology (CCET)》;全文 *
基于边缘智能协同的天地一体化信息网络研究;周旭;李泰新;覃毅芳;宋俊平;;电信科学(第07期);全文 *

Also Published As

Publication number Publication date
CN114826937A (en) 2022-07-29

Similar Documents

Publication Publication Date Title
Qian et al. Survey on reinforcement learning applications in communication networks
CN111132235B (en) Mobile offload migration algorithm based on improved HRRN algorithm and multi-attribute decision
CN112187891B (en) Load optimization method and device of edge computing node set based on multiple services
Chen et al. Learning-based computation offloading for IoRT through Ka/Q-band satellite–terrestrial integrated networks
CN109639833A (en) A kind of method for scheduling task based on wireless MAN thin cloud load balancing
CN113946436B (en) Resource pre-scheduling method based on load balancing
Wang et al. Radio resource allocation for bidirectional offloading in space-air-ground integrated vehicular network
CN113676357B (en) Decision method for edge data processing in power internet of things and application thereof
CN115967990A (en) Classification and prediction-based border collaborative service unloading method
Ali et al. EEOMA: End-to-end oriented management architecture for 6G-enabled drone communications
CN114826937B (en) Flow sensing method based on size time scale under world integration network
CN114338675A (en) Remote sensing satellite big data processing method and system based on edge calculation
Gill et al. On the capacity bounds for bumblebee-inspired connected vehicle networks via queuing theory
US10568047B2 (en) Base station sleep mode based on powder consumption and/or quality of service
CN112969157B (en) Network load balancing method for unmanned aerial vehicle
CN116017611A (en) Network selection method considering terminal application experience in air-space heterogeneous network
CN115499875A (en) Satellite internet task unloading method and system and readable storage medium
Sundari et al. Three node tandem communication network model with dynamic bandwidth allocation and Non Homogeneous Poisson arrivals
CN113015109B (en) Wireless virtual network access control method in vehicle fog calculation
CN104661261A (en) Dynamic flow unloading method based on state of heterogeneous wireless network and dynamic flow unloading system based on state of heterogeneous wireless network
Messaoud et al. In-depth performance evaluation of network slicing strategies in large scale industry 4.0
CN107659501A (en) Efficiency optimized transmission method and system based on complicated gradient network
Keshav et al. Call admission control for interactive multimedia in 5g networks
Zhang et al. A QoS aware uplink scheduler for IoT in emergency over LTE/LTE-A networks
Cao et al. Research on Edge Resource Allocation Method Based on Vehicle Trajectories Prediction

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