CN118400276B - Communication network oscillation analysis system and method - Google Patents
Communication network oscillation analysis system and method Download PDFInfo
- Publication number
- CN118400276B CN118400276B CN202410869863.6A CN202410869863A CN118400276B CN 118400276 B CN118400276 B CN 118400276B CN 202410869863 A CN202410869863 A CN 202410869863A CN 118400276 B CN118400276 B CN 118400276B
- Authority
- CN
- China
- Prior art keywords
- network
- link
- data
- communication
- oscillation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 225
- 230000010355 oscillation Effects 0.000 title claims abstract description 116
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 48
- 238000004364 calculation method Methods 0.000 claims description 46
- 230000007704 transition Effects 0.000 claims description 28
- 230000009514 concussion Effects 0.000 claims description 26
- 238000013210 evaluation model Methods 0.000 claims description 22
- 230000006378 damage Effects 0.000 claims description 16
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 abstract description 6
- 239000007787 solid Substances 0.000 abstract description 6
- 238000004088 simulation Methods 0.000 abstract 1
- 239000011159 matrix material Substances 0.000 description 6
- 230000003993 interaction Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000002427 irreversible effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 235000008694 Humulus lupulus Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
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
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a system and a method for analyzing oscillation of a communication network, the system comprises an input module, an interference module and a network oscillation analysis module. The method constructs a communication network from a data plane and a control plane by acquiring initial network configuration information; based on the network interference information and different network configuration information, network oscillation simulation is carried out on the communication network, and network performance after the communication network is subjected to network oscillation under different network configuration conditions is calculated and analyzed to obtain network performance information. Therefore, by utilizing the technical scheme provided by the invention, the real situation-based communication network is constructed, when external interference is received, the influence factors of the communication network oscillation are found out by analyzing the performance of the communication network under different network configuration conditions, and a solid foundation is laid for optimizing the network design and improving the network robustness.
Description
Technical Field
The invention relates to the technical field of communication networks, in particular to a system and a method for analyzing oscillation of a communication network.
Background
Network concurrency typically occurs in a network environment with dynamic routing protocols that attempt to recalculate the best path when a router or link fails or breaks down. This may lead to path changes and traffic redistribution, thereby causing network oscillations to occur. The essential reason is that because inconsistent routing decisions and network topology change too quickly, when routers are added or deleted, link capacity is adjusted, etc., dynamic routing protocols may not be able to adapt to these changes in time, and different routers may select different forwarding paths according to their own routing information. If the routing decisions between these routers are inconsistent, traffic may be repeatedly forwarded back and forth in the network, causing network oscillation.
In order to solve the problem of network oscillation, a system and a method for analyzing the communication network oscillation are needed to find out the influence factors of the communication network oscillation, and a solid foundation is laid for optimizing the network design and improving the network robustness.
Disclosure of Invention
In order to solve the problems, the invention discloses a communication network oscillation analysis system and a communication network oscillation analysis method.
To achieve the above object, in a first aspect of the present invention, a system for analyzing oscillation of a communication network is disclosed, the system comprising: the system comprises an input module, an interference module and a network oscillation analysis module;
The input module is used for inputting initial network configuration information and sending the initial network configuration information to the network oscillation analysis module; the initial network configuration information comprises router information, link information, routing strategy and gateway information; the router information comprises a router queue size, whether the router queue is a gateway or not and the like; the link information comprises the bandwidth size of the link and the like; the routing strategies comprise a shortest path strategy, a minimum degree strategy, a congestion avoidance strategy and the like; the gateway information includes the communication flow between hosts, the data size of the communication flow, and the like.
The interference module is used for generating network interference information and sending the network interference information to the network oscillation analysis module; the network interference information includes random damage and malicious damage.
The network oscillation analysis module comprises: a network communication model, a network concussion random model and a network performance evaluation model.
The network communication model is used for constructing a communication network and comprises a data plane unit, a control plane unit, a network configuration unit and a traffic density unit; the data plane unit is used for constructing an initial communication network from a data plane; the control plane unit is used for carrying out network load configuration on the initial communication network from a control plane; the network configuration unit is used for generating different network configurations according to the initial network configuration information; the traffic density unit is used to configure the bandwidth and queue size of links in the communication network.
The network oscillation random model is used for processing the communication network according to the network configuration information and the network interference information and generating an oscillation network; the network concussion random model comprises: a link state classification unit and a link state transfer unit; the link state classification unit is used for classifying routers in the communication network; the link state transition unit is used for calculating the link state transition probability in the communication network and updating all routers in the communication network.
The network performance evaluation model is used for performing performance evaluation on the oscillating network and generating network performance data; the network performance data comprises network flow-level throughput real-time data, link-level packet loss number data, network oscillation duration data, gateway connectivity rate data and normal link proportion data; the flow-level throughput real-time computing unit is used for computing network real-time throughput variation in the communication network, the link-level packet loss number computing unit is used for computing packet loss number of each link in the communication network, the network oscillation duration computing unit is used for computing network oscillation duration in the communication network, and the gateway connectivity rate computing unit is used for computing connectivity rates among gateways in the communication network; the normal link ratio calculating unit is used for calculating the normal link ratio in the communication network.
The second aspect of the embodiment of the invention discloses a communication network oscillation analysis method, which is applied to the system disclosed by the first aspect of the embodiment of the invention, and comprises the following steps:
S1, generating network interference information by using an interference module; the network interference information comprises random damage and malicious damage;
s2, acquiring initial network configuration information by using an input module; the initial network configuration information comprises router information, link information, routing strategy, gateway information and the like;
s3, generating a communication network by using a network communication model according to the initial network configuration information;
s4, generating a network configuration information set by using a network configuration unit based on the initial network configuration information; the network configuration information set comprises a plurality of network configuration information;
s5, traversing the network configuration information set based on the network interference information, and processing the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance information; the network performance information characterizes network performance under different network configuration information.
As an optional implementation manner, the generating a communication network according to the initial network configuration information by using a network communication model includes:
s31, constructing an initial communication network by utilizing a data plane unit in the network;
The initial communication network G is represented as:
G＝(R,L)
Where r= { R i i=1, 2,..n } represents the set of routers, and R i represents the i-th router; n represents the number of routers included in the network; l= { L j |j=1, 2,..m } represents a set of communication links, L j represents a j-th link; m represents the number of communication links included in the network.
The adjacency matrix A of the initial communication network G is represented as
A＝(aur)N×N
Wherein a represents an adjacency matrix of the initial communication network G, and a ur represents a connection relationship between a router u and a router r in the initial communication network G; if there is a link between router u and router r, then the adjacency matrix is a ur =1, otherwise a ur =0;
The set of communication flows F in the initial communication network G is:
F＝{fi|i∈(1,...,nf)}
Wherein n f characterizes the total number of inter-host communication flows; the host characterizes any terminal in the initial communication network G; the communication flow F characterizes communication data flow between hosts;
The communication flow f i can be defined as a sequence of all routers and links through which it passes, making up a tuple:
Wherein, the F r(fi, j) and F l(fi, j) are denoted as the j-th router and link traversed along the communication flow F i, |f i | is denoted as the last router and link traversed by the communication flow F i;
S32, carrying out network load configuration on the initial communication network by utilizing a control plane unit according to a preset routing strategy;
S33, configuring the bandwidth and the queue size of the link in the initial communication network by utilizing the traffic density unit, and realizing the trusted network initial capacity configuration to obtain the communication network.
As an optional implementation manner, the configuring, according to a preset routing policy, the network load of the initial communication network by using a control plane unit includes:
S321, calculating a communication flow set in the initial communication network by using a control plane unit to obtain a data packet generation rate of the communication flow; the communication flow characterizes communication data flow between hosts; the host characterizes any terminal in the initial communication network;
S322, processing the link set by using a control plane unit to obtain a link load information set; the set of links characterizes a set of all links in the initial communication network; the router load information set comprises a plurality of link load information;
the link load information is:
Wherein L i (t) represents link i load information at time t; q i (t-1) is the remaining packets in the queue to which link i corresponds at time t-1, F (i) is the set of traffic flows through link i, The packet arrival rate for the communication flow f k to reach link i at time t;
The arrival rate of the data packet of the communication flow f k reaching the link i at the time t is related to the arrival rate of the data packet at the time t-1, the link bandwidth and the queue size, and is expressed as follows:
where y is the previous link from which the traffic arrives at link i, The packet arrival rate at link y for communication flow f k at time t-1,For the packet arrival rate of all flows t-1 arriving at link y at time, L y (t-1) is the load of link y at time t-1; b y is the bandwidth of link y;
S323, processing the link set by using a control plane unit to obtain a link weight; specifically, the weight w i (t) of link i at time t, said weight w i (t) characterizing the congestion situation of the communication flow as it passes through link i, i.e.
Where B i is the bandwidth of link i and L i (t) is the load size of link i at time t.
As an optional implementation manner, the traffic density unit is used for configuring the bandwidth and the queue size of the link in the initial communication network, so as to realize the trusted network initial capability configuration and obtain the communication network;
The link bandwidth is:
Wherein B i is the bandwidth of link i; an average packet transmission rate for traffic flow f i; alpha is a tolerance coefficient of the bandwidth rate, and the margin of the link bandwidth compared with the normal running state is controlled; f (i) is a set of traffic flows over link i;
The queue size is:
Qi＝(1+β)·max{[Li(t)-Bi],t∈T},β≥0
wherein Q i is the queue size of link i; max { [ L i(t)-Bi ], T epsilon T } is the maximum data residual length of load exceeding the bandwidth size in time T, beta is the tolerance coefficient of the queue size, and the margin degree of the queue size compared with the normal running state is controlled;
the data residual length calculation formula is as follows:
Wherein, L i(t)＞Bi is that the link load L i (t) is larger than the link bandwidth B i at the moment of t, which indicates that data packets remain in the queue, and the value of [ L i(t)-Bi ] is L i(t)-Bi; conversely, [ L i(t)-Bi ] has a value of 0.
As an optional implementation manner, traversing the network configuration information set based on the network interference information, and processing the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance information, where the processing includes:
S51, any unselected network configuration information is obtained from the network configuration information set;
S52, processing the communication network by utilizing a network concussion random model and a network performance evaluation model based on the any unselected network configuration information and the network interference information to obtain network performance data corresponding to the any unselected network configuration information; the network performance data comprise network flow-level throughput real-time data, link-level packet loss data, network oscillation duration data, gateway connectivity rate data and normal link proportion data;
S53, traversing the network configuration information set, and if the network configuration information set has unselected network configuration information, turning to step S51; if the network configuration information set has no unselected network configuration information, go to step S54;
and S54, integrating all network performance data corresponding to the network configuration information in the network configuration information set to obtain network performance information.
As an optional implementation manner, the processing, based on the any unselected network configuration information and the network interference information, the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance data corresponding to the any unselected network configuration information includes:
S521, processing the communication network by using a network oscillation random model based on the any unselected network configuration information and the network interference information to obtain an oscillation network;
S522, processing the oscillation network by using a network performance evaluation model to obtain network performance data corresponding to any unselected network configuration information.
As an optional implementation manner, the processing the communication network by using a network oscillation random model based on the any unselected network configuration information and the network interference information to obtain an oscillation network includes:
S5211, identifying the link state in the communication network by using a link state classification unit according to any unselected network configuration information and the network interference information to obtain a link state information set; the set of link state information includes state information corresponding to all links in the communication network; the link state information is normal, or, congestion, or overload;
S5212, calculating link state transition in a network by using a link state transition unit to obtain a link state transition probability set; the set of link state transition probabilities includes state transition probabilities corresponding to all links in the communication network;
S5213, updating all routers in the communication network by a link state transition unit according to the link state information set and the link state transition probability set to obtain an oscillation network.
As an optional implementation manner, the processing the oscillating network by using a network performance evaluation model to obtain network performance information, to obtain network performance data corresponding to the any unselected network configuration information, includes:
S5221, processing the oscillation network by using a stream-level throughput real-time computing unit to obtain network stream-level throughput real-time data; the real-time data of the network flow level throughput represents the number of data packets successfully forwarded by all network flows in the network;
The network flow level throughput real-time data calculation formula is:
where F is the set of all traffic flows in the network, Packet arrival rate for the t-time traffic flow f i to reach the last, i.e., the |f i | router.
S5222, processing the oscillating network by using a link-level packet loss number calculation unit to obtain link-level packet loss number data; the link-level packet loss data represents packet loss data of each link in a network; the specific calculation method comprises the following steps:
At time t, the calculation formula of the packet loss number loss i (t) of the link i is as follows:
lossi(t)＝Li(t)-Bi-Qi
Where L i (t) is time link i load information, B i represents the bandwidth size of link i, and Q i represents the queue size of the router in link i.
S5223, processing the oscillation network by using a network oscillation duration calculation unit to obtain network oscillation duration data; the network concussion duration data is expressed as the difference between the time after the network is attacked and the time after the network is stabilized.
S5224, processing the oscillation network by using a gateway connectivity calculation unit to obtain gateway connectivity data; the gateway connectivity data characterizes network gateway connectivity; at time t, a specific calculation method for calculating gateway connectivity C gate (t) in the oscillation network is as follows:
Wherein C gate (t) represents time t, oscillates gateway connectivity in the network, describes network gateway connectivity (single-hop or multi-hop) at time t, describes the capability of the network to provide connectivity services, G (t) is the network at time t, G is the connected subgraph of G, and h g is the number of gateways in the connected subgraph G.
S5225, processing the oscillating network by using a normal link proportion calculation unit to obtain normal link proportion data; the normal link proportion data represents the ratio of the number of links in a normal state in the oscillating network to the total number of links in the oscillating network; specifically, the normal link ratio Ln (t) at time t is calculated as follows:
Wherein Ln (t) represents normal link proportion data at time t, M represents the total number of links in the oscillating network, L represents a link set in the oscillating network, and L i (t) =normal table link L i is in a normal state at time t.
S5226, integrating the network flow-level throughput real-time data, the link-level packet loss number data, the network oscillation duration time data, the gateway connectivity rate data and the normal link proportion data to obtain network performance data corresponding to any unselected network configuration information.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
the embodiment of the invention discloses a communication network oscillation analysis system and a communication network oscillation analysis method, which are used for analyzing the network oscillation condition after a communication network is faced with faults, further determining key factors influencing network oscillation through control variables, and controlling the operation of a system by inputting external interference, a network communication model and a network oscillation random model to respond to the external interference, wherein a network performance evaluation model is used for analyzing the network performance change when the network is stable, so that the oscillation network is a performance index. Therefore, by utilizing the technical scheme provided by the invention, the real situation-based communication network is constructed, when external interference is received, the influence factors of the communication network oscillation are found out by analyzing the performance of the communication network under different network configuration conditions, and a solid foundation is laid for optimizing the network design and improving the network robustness.
Drawings
Fig. 1 is a schematic structural diagram of a communication network oscillation analysis system according to an embodiment of the present invention;
Fig. 2 is a flowchart of a method for analyzing oscillation of a communication network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Abbreviation and key term definitions
A communication network. Refers to a network system consisting of a plurality of nodes, which may be computers, routers, servers, sensors, personnel, etc., and connections between them.
A data plane. Refers to the portion of the network device that is responsible for actually processing and forwarding the data stream. The data plane performs a forwarding operation of the data packet, forwarding the data packet from the input port to the appropriate output port according to a pre-configured rule.
And a control plane. Refers to the portion responsible for managing and controlling the behavior of the network device. It includes software, protocols, and algorithms running on the network device to configure, monitor, and maintain the status and behavior of the network device.
External interference. When the network is subject to external interference, some routers in the network may be damaged, and the network topology changes. This will trigger a change in the network traffic path, which in turn leads to a cascading failure. In order to trigger network oscillation, the invention mainly considers two network fault types, namely random damage and malicious damage. We define the ratio of the number of failed routers to the total number of routers as: random failures randomly select routers to remove from the network. This type of failure may simulate a network that is subject to natural disasters (e.g., hurricane sandi, 2008 china earthquake). Malicious attacks, which select nodes based on importance/criticality metrics, may be caused by human disasters (e.g., APT attacks). The present invention uses node degree as an index (called degree attack). The degree attack sorts all routers in the network according to degrees, and the router removal sequence operates according to the sequence from big to small of illumination on the premise that the attack rate is not exceeded.
Performance index. Analyzing network performance from different perspectives may substantially reflect the performance characteristics of complex dynamic communication networks. The technical scheme provided by the invention analyzes the change of network performance from 5 aspects of stream-level real-time throughput, link-level packet loss, network oscillation duration, gateway connectivity and normal link proportion.
Network concussion: refers to an unstable phenomenon that occurs in computer networks and is characterized by network traffic repeatedly fluctuating or oscillating back and forth in the network. Network concurrency typically occurs in a network environment having dynamic routing protocols, such as large enterprise networks or internet service provider networks using OSPF or BGP, among others.
Network concurrency typically occurs in a network environment with dynamic routing protocols that attempt to recalculate the best path in the network when a router fails or a link is broken. This may lead to path changes and traffic redistribution, thereby causing network oscillations to occur.
Aiming at the problems of insufficient existing network oscillation analysis methods and unclear network oscillation influence factors, the complex dynamic communication network oscillation analysis method based on multi-plane interaction is provided, a network oscillation analysis model is constructed, the network oscillation influence factors are analyzed from the angle of the interaction of a data plane and a control plane, and a solid foundation is laid for optimizing network design and improving network robustness.
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Example 1
Please refer to fig. 1. Fig. 1 is a schematic structural diagram of a communication network oscillation analysis system according to an embodiment of the present invention.
As shown in fig. 1, the embodiment of the invention discloses a system for analyzing oscillation of a communication network, which comprises:
The input module 10 is configured to input initial network configuration information and send the initial network configuration information to the network concussion analysis module 30; the initial network configuration information comprises router information, link information, routing strategy and gateway information; the router information comprises a router queue size, whether the router is a gateway or not and the like; the link information comprises the bandwidth size of the link and the like; the routing strategies comprise a shortest path strategy, a minimum degree strategy, a congestion avoidance strategy and the like; the gateway information includes the communication flow between hosts, the data size of the communication flow, and the like.
The interference module 20 is configured to generate network interference information, and send the network interference information to the network oscillation analysis module 30; the network interference information includes random damage and malicious damage.
The network concussion analysis module 30 includes a network communication model 301, a network concussion random model 302, and a network performance evaluation model 303;
The network communication model 301 is used to construct a communication network, and includes: a data plane unit 3011, a control plane unit 3012, a network configuration unit 3013, and a traffic density unit 3014; the data plane unit 3011 is configured to construct an initial communication network having complex dynamic communication network properties from a data plane; the control plane unit 3012 is configured to perform network load configuration on the initial communication network from a control plane; the network configuration unit 3013 is configured to generate different network configurations according to the initial network configuration information; the traffic density unit 3014 is configured to configure a bandwidth and a queue size of a link in the communication network.
The network concussion random model 302 is configured to process a communication network according to network configuration information and network interference information, and generate a concussion network, and includes: a link state classification unit 3021 and a link state transition unit 3022; the above-mentioned link state classification unit 3021 is used for classifying routers in a communication network; the link state transition unit 3022 is configured to calculate a link state transition probability in the communication network and update all routers in the communication network.
The network performance evaluation model 303 is configured to perform performance evaluation on the oscillating network to obtain network performance data, and includes: the flow-level throughput real-time calculation unit 3031, the link-level packet loss calculation unit 3032, the network oscillation duration calculation unit 3033, the gateway connectivity rate calculation unit 3034 and the normal link proportion calculation unit 3035, wherein the network performance data comprise network flow-level throughput real-time data, link-level packet loss data, network oscillation duration data, gateway connectivity rate data and normal link proportion data;
The flow-level throughput real-time calculation unit 3031 is configured to calculate a real-time throughput change of a network in the communication network, the link-level packet loss number calculation unit 3032 is configured to calculate a packet loss number of each link in the communication network, the network oscillation duration calculation unit 3033 is configured to calculate a network oscillation duration in the communication network, and the gateway connectivity rate calculation unit 3034 is configured to calculate a connectivity rate between gateways in the communication network; the normal link ratio calculating unit 3035 is configured to calculate a normal link ratio in the communication network.
Example two
The second aspect of the embodiment of the invention discloses a communication network oscillation analysis method which is applied to the communication network oscillation analysis system disclosed by the embodiment of the invention.
Please refer to fig. 2. Fig. 2 is a flowchart of a method for analyzing oscillation of a communication network according to an embodiment of the present invention. As shown in fig. 2, a method for analyzing oscillation of a communication network according to an embodiment of the present invention includes:
S1, generating network interference information by using an interference module; the network interference information comprises random damage and malicious damage;
S2, acquiring initial network configuration information by using an input module; the initial network configuration information comprises router information, link information, routing strategy and gateway information;
S3, generating a communication network by using a network communication model according to the initial network configuration information;
s4, generating a network configuration information set by using a network configuration unit based on the initial network configuration information; the network configuration information set comprises a plurality of network configuration information;
S5, traversing a network configuration information set based on the network interference information, and processing the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance information; the network performance information characterizes network performance under different network configuration information.
It should be noted that, the network performance is reflected under different network configurations when the network oscillates, so as to find out the influencing factors of the communication network oscillation, and lay a solid foundation for optimizing the network design and improving the network robustness.
Therefore, according to the communication network oscillation analysis method described in the embodiment, network oscillation influence factors are analyzed from the angle of interaction between the data plane and the control plane, the influence of network oscillation on network performance under different configuration conditions is generated, and a solid foundation is laid for optimizing network design and improving network robustness.
In another optional embodiment, the generating a communication network according to the initial network configuration information using a network communication model includes:
s31, constructing an initial communication network by utilizing a data plane unit in the network;
The initial communication network G is represented as:
G＝(R,L)
Where r= { R i i=1, 2,..n } represents the set of routers, and R i represents the i-th router; n represents the number of routers included in the network; l= { L j | j=1, 2, …, M } represents the set of communication links, L j represents the j-th link; m represents the number of communication links included in the network.
The adjacency matrix A of the initial communication network G is represented as
A＝(aur)N×N
Wherein a represents an adjacency matrix of the initial communication network G, and a ur represents a connection relationship between a router u and a router r in the initial communication network G; if there is a link between router u and router r, then the adjacency matrix is a ur =1, otherwise a ur =0;
The set of communication flows F in the initial communication network G is:
F＝{fi|i∈(1,...,nf)}
Wherein n f characterizes the total number of inter-host communication flows; the host characterizes any terminal in the initial communication network G; the communication flow F characterizes communication data flow between hosts;
The communication flow f i can be defined as a sequence of all routers and links through which it passes, making up a tuple:
Wherein, F r(fi, j) and F l(fi, j) are denoted as the j-th router and link traversed along the communication flow fi, and |f i | is denoted as the last router and link traversed by the flow F i.
It should be noted that the architecture of the communication network system may be divided into a routing layer and a device layer. The equipment layer is composed of a large number of hosts, including mobile phones, computers, automobiles, servers and the like, and the hosts are accessed into a communication network by using a gateway and mutually communicated to form a communication flow. The routing layer is composed of routers and communication links and is mainly responsible for transmitting data packets. There are two classes of routers in a network, including gateways and ordinary routers. The general router is responsible for storing and forwarding data packets according to a routing protocol. The gateway is connected with the host computer and gathers data packets from the host computer. Thus, communications between hosts may be fully mapped to the routing layer according to the routing protocol.
S32, carrying out network load configuration on the initial communication network by utilizing a control plane unit according to a preset routing strategy;
S33, configuring the bandwidth and the queue size of the link in the initial communication network by utilizing the traffic density unit, and realizing the trusted network initial capacity configuration to obtain the communication network.
In yet another alternative embodiment, the configuring the network load of the initial communication network by using a control plane unit according to a preset routing policy includes:
S321, calculating a communication flow set in the initial communication network by using a control plane unit to obtain a data packet generation rate of the communication flow; the communication flow characterizes communication data flow between hosts; the host characterizes any terminal in the initial communication network;
S322, processing the link set by using a control plane unit to obtain a link load information set; the set of links characterizes a set of all links in the initial communication network; the router load information set comprises a plurality of link load information;
the link load information is:
Wherein L i (t) represents link i load information at time t; q i (t-1) is the remaining packets in the queue to which link i corresponds at time t-1, F (i) is the set of traffic flows through link i, The packet arrival rate for the communication flow f k to reach link i at time t;
The arrival rate of the data packet of the communication flow f k reaching the link i at the time t is related to the arrival rate of the data packet at the time t-1, the link bandwidth and the queue size, and is expressed as follows:
where y is the previous link from which the traffic arrives at link i, The packet arrival rate at link y for communication flow f k at time t-1,For the packet arrival rate of all traffic flows t-1 arriving at link y at time, L y (t-1) is the load of link y at time t-1; b y is the bandwidth of link y;
S323, processing the link set by using a control plane unit to obtain a link weight; specifically, the weight w i (t) of link i at time t, said weight w i (t) characterizing the congestion situation of the communication flow as it passes through link i, i.e.
Where B i is the bandwidth of link i and L i (t) is the load size of link i at time t.
It should be noted that the processing of the data packet by each host is divided into 4 parts, namely, data packet generation, data packet transmission, data packet discarding and data packet releasing. At each time step, the packet generation rate of the communication stream is set toThe dependent routing layer paths are determined according to the routing strategy, and the method mainly considers three types of routes of the shortest path, the minimum number and the congestion avoidance.
Shortest path routing is the path that looks for the smallest number of hops from the source host to the destination host. If there are multiple shortest paths in the network, the model randomly selects one.
Minimum degree routing, the goal is to minimize the sum of the degrees of all routers on the path. Since routers with the greatest degree tend to generate congestion, the minimum degree routing strategy can control congestion and redistribute load from a central router to other non-central routers.
Congestion avoidance routing, finding the route with the least congestion from the source host to the destination host, aims at the least sum of congestion weights of all routers on the path.
During the packet transmission, the router i forwards the packet to the next hop with the bandwidth of B i according to the first-in-first-out (FIFO) principle. At the same time, each router has a queue Q i for storing packets. When the total number of packets on the queue is reached, the unprocessed packets will be discarded. If the packets have arrived at the target host, they will be released from the queue. The load of the router i at the t moment is the sum of the rest data packets in the queue, the last transmitted data packets of the neighbor routers and the data packets generated by the host at the t moment.
In yet another alternative embodiment, the traffic density unit is used to configure the bandwidth and queue size of the link in the initial communication network, so as to implement trusted network initial capability configuration, and obtain the communication network;
The link bandwidth is:
Wherein B i is the bandwidth of link i; an average packet transmission rate for traffic flow f i; alpha is a tolerance coefficient of the bandwidth rate, and the margin of the link bandwidth compared with the normal running state is controlled; f (i) is a set of traffic flows over link i;
The queue size is:
Qi＝(1+β)·max{[Li(t)-Bi],t∈T},β≥0
wherein Q i is the queue size of link i; max { [ L i(t)-Bi ], T epsilon T } is the maximum data residual length of load exceeding the bandwidth size in time T, beta is the tolerance coefficient of the queue size, and the margin degree of the queue size compared with the normal running state is controlled;
The data residual length calculation formula is
Wherein, L i(t)＞Bi is that the link load L i (t) is larger than the link bandwidth B i at the moment of t, which indicates that data packets remain in the queue, and the value of [ L i(t)-Bi ] is L i(t)-Bi; conversely, [ L i(t)-Bi ] has a value of 0.
In the communication network, the traffic density is the ratio of the rate at which data arrives at the queue to the forwarding rate. The golden rule in flow engineering is: the flow strength cannot be greater than 1 when the system is designed. The network is in a free-flow state before s is damaged. In the free flow state, no packet loss and no oscillation exist in the network. Thus, the packet arriving at time t may be held in the queue and the transmission completed. Our model assumes that the initial transmission rate and buffer of a router are linearly related to the maximum load of the router. And if the maximum load of the router is 0, setting the basic transmission rate and the buffer memory according to the number of the neighbor routers.
In yet another optional embodiment, the traversing the network configuration information set based on the network interference information, and processing the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance information includes:
S51, any unselected network configuration information is obtained from the network configuration information set;
S52, processing the communication network by utilizing a network concussion random model and a network performance evaluation model based on the any unselected network configuration information and the network interference information to obtain network performance data corresponding to the any unselected network configuration information; the network performance data comprise network flow-level throughput real-time data, link-level packet loss data, network oscillation duration data, gateway connectivity rate data and normal link proportion data;
S53, traversing the network configuration information set, and if the network configuration information set has unselected network configuration information, turning to step S51; if the network configuration information set has no unselected network configuration information, go to step S54;
And S54, integrating all network performance data corresponding to the network configuration information in the network configuration information set, namely, sorting and comprehensively analyzing the network performance data under different network configuration information to obtain the network performance information, wherein the network performance information integrally presents the network performance data under different network configuration information to a user, and the user selects different network configurations according to different network requirements.
In yet another optional embodiment, the processing, based on the any unselected network configuration information and the network interference information, the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance data corresponding to the any unselected network configuration information includes:
S521, processing the communication network by using a network oscillation random model based on the any unselected network configuration information and the network interference information to obtain an oscillation network;
S522, processing the oscillation network by using a network performance evaluation model to obtain network performance data corresponding to any unselected network configuration information.
In yet another optional embodiment, the processing the communication network by using a network oscillation random model based on the any unselected network configuration information and the network interference information to obtain an oscillation network includes:
S5211, identifying the link state in the communication network by using a link state classification unit according to any unselected network configuration information and the network interference information to obtain a link state information set; the set of link state information includes state information corresponding to all links in the communication network; the link state information is normal, or, congested, or overloaded.
It should be noted that overload of routers in the communication network does not cause irreversible physical damage, and packet loss is a major negative effect. The sender must retransmit to supplement the lost packets due to queue overflow, and more packets will fill the entire network, resulting in network congestion. When an arriving packet exceeds the processing power of the router, the router may become overloaded and inoperable due to congestion.
The method uses the link stateDefined as three possible states, normal, congestion and overload, expressed as:
Where r i denotes router i, normal denotes normal, congestion denotes congestion, and overload denotes overload.
Before the links are damaged, the network is in a free-flow state, and each link normally stores and forwards arriving packets. When the link is damaged, the router can carry out rerouting to change the network communication path, and the occurrence of rerouting further causes network oscillation to reduce the network performance. This will further change the distribution of network load, overloading more links with congestion. When the link does not lose the packet, the router is in normal state, and can normally operate. If the corresponding queue of the link is too small or the transmission speed is too slow, packets arriving at the link may be dropped, i.e. in a congested state, i.e. the link cannot process the arriving packets in time. In general, the more links that are dropped than the fewer dropped links are more likely to be overloaded. When the link is overloaded, data packets cannot be generated, transmitted, and received.
S5212, calculating link state transition in a network by using a link state transition unit to obtain a link state transition probability set; the set of link state transition probabilities includes state transition probabilities corresponding to all links in the communication network.
S5213, updating all routers in the communication network by a link state transition unit according to the link state information set and the link state transition probability set to obtain an oscillation network.
Setting gamma i (t) as overload probability of link i at time t overload, wherein the probability is in direct proportion to the number of lost packets of the link and the overload rate of a basic unit, and in inverse proportion to the size of a router queue
Where a i is the basic unit overload rate, which is related to the performance of the router i, such as heat dissipation capability, CPU performance, etc., L i(t)-Bi represents the packet loss number of the link i at time t, L i (t) is the load information of the router i at time t, B i represents the bandwidth size of the link i, and Q i represents the queue size on the router i. As can be seen from the above formula, the failure probability of the cache router is lower, and the high-performance router has higher stability. But overload of the link is not an irreversible physical damage and the link will recover after the time arrives. When Δt expires, the link will resume normal operation. When Δt approaches a unit time, it means that the overloaded link can be immediately restored to a normal state. When Δt approaches +. alpha., the link will be permanently removed from the network directly.
In yet another optional embodiment, the processing the oscillating network with the network performance evaluation model to obtain network performance information, to obtain network performance data corresponding to the any unselected network configuration information, includes:
S5221, processing the oscillation network by using a stream-level throughput real-time computing unit to obtain network stream-level throughput real-time data; the real-time data of the network flow level throughput represents the number of data packets successfully forwarded by all network flows in the network;
The network flow level throughput real-time data calculation formula is:
where F is the set of all traffic flows in the network, Packet arrival rate for the t-time traffic flow f i to reach the last, i.e., the |f i | router.
S5222, processing the oscillating network by using a link-level packet loss number calculation unit to obtain link-level packet loss number data; the link-level packet loss data represents packet loss data of each link in a network; the specific calculation method comprises the following steps:
At time t, the calculation formula of the packet loss number loss i (t) of the link i is as follows:
lossi(t)＝Li(t)-Bi-Qi
Where L i (t) is time link i load information, B i represents a bandwidth size of link i, and Q i represents a queue size of a router in link i.
S5223, processing the oscillation network by using a network oscillation duration calculation unit to obtain network oscillation duration data; the network concussion duration data is expressed as the difference between the time after the network is attacked and the time after the network is stabilized.
S5224, processing the oscillation network by using a gateway connectivity calculation unit to obtain gateway connectivity data; the gateway connectivity data characterizes network gateway connectivity; at time t, a specific calculation method for calculating gateway connectivity C gate (t) in the oscillation network is as follows:
Wherein C gate (t) represents time t, oscillates gateway connectivity in the network, describes network gateway connectivity (single-hop or multi-hop) at time t, describes the capability of the network to provide connectivity services, G (t) is the network at time t, G is the connected subgraph of G, and h g is the number of gateways in the connected subgraph G.
S5225, processing the oscillating network by using a normal link proportion calculation unit to obtain normal link proportion data; the normal link proportion data represents the ratio of the number of links in a normal state in the oscillating network to the total number of links in the oscillating network; specifically, the normal link ratio Ln (t) at time t can be calculated as follows:
Wherein Ln (t) represents normal link proportion data at time t, M represents the total number of links in the oscillating network, L represents a link set in the oscillating network, and L i (t) =normal table link L i is in a normal state at time t.
S5226, integrating the network flow-level throughput real-time data, the link-level packet loss number data, the network oscillation duration time data, the gateway connectivity rate data and the normal link proportion data to obtain network performance data corresponding to any unselected network configuration information.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable ReadOnly Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a communication network oscillation analysis system and a communication network oscillation analysis method, which are only disclosed as the preferred embodiment of the invention, and are only used for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (5)
1.A method for analyzing oscillation of a communication network, the method comprising:
S1, generating network interference information by using an interference module; the network interference information comprises random damage and malicious damage;
S2, acquiring initial network configuration information by using an input module; the initial network configuration information comprises router information, link information, routing strategy and gateway information;
s3, generating a communication network by using a network communication model according to the initial network configuration information;
s4, generating a network configuration information set by using a network configuration unit based on the initial network configuration information; the network configuration information set comprises a plurality of network configuration information;
S5, traversing the network configuration information set based on the network interference information, and processing the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance information; specifically:
S51, any unselected network configuration information is obtained from the network configuration information set;
S52, based on the any unselected network configuration information and the network interference information, processing the communication network by using a network concussion random model and a network performance evaluation model to obtain network performance data corresponding to the any unselected network configuration information, including:
S521, processing the communication network by using a network oscillation random model based on the any unselected network configuration information and the network interference information to obtain an oscillation network;
S522, processing the oscillation network by using a network performance evaluation model to obtain network performance data corresponding to any unselected network configuration information, including:
s5221, processing the oscillation network by using a stream-level throughput real-time computing unit to obtain network stream-level throughput real-time data; the real-time data of the network flow level throughput represents the number of data packets successfully forwarded by all network flows in the network; the specific calculation method comprises the following steps:
the network flow level throughput real-time data calculation formula is:
where F is the set of all traffic flows in the network, Packet arrival rate for t-time traffic flow f i to reach the last, i.e., the |f i | router;
S5222, processing the oscillating network by using a link-level packet loss number calculation unit to obtain link-level packet loss number data; the link-level packet loss data represents packet loss data of each link in a network; the specific calculation method comprises the following steps:
At time t, the calculation formula of the packet loss number loss i (t) of the link i is as follows:
lossi(t)＝Li(t)-Bi-Qi
Wherein, L i (t) is load information of a time link i, B i represents bandwidth size of the link i, and Q i represents queue size of a router in the link i;
s5223, processing the oscillation network by using a network oscillation duration calculation unit to obtain network oscillation duration data; the network oscillation duration time data represents the difference value between the time after the network is attacked and the time after the network is stabilized;
s5224, processing the oscillation network by using a gateway connectivity calculation unit to obtain gateway connectivity data; the gateway connectivity data characterizes network gateway connectivity; at time t, a specific calculation method for calculating gateway connectivity C gate (t) in the oscillation network is as follows:
Wherein C gate (t) represents the gateway rate at time t, G (t) is the network at time t, G is the connected subgraph of G, and h g is the number of gateways in the connected subgraph G;
S5225, processing the oscillating network by using a normal link proportion calculation unit to obtain normal link proportion data; the normal link proportion data represents the ratio of the number of links in a normal state in the oscillating network to the total number of links in the oscillating network; the normal link ratio Ln (t) at time t is calculated as follows:
Wherein Ln (t) represents normal link proportion data at time t, M represents the total number of links in the oscillating network, L represents a link set in the oscillating network, and L i (t) =normal table link L i is in a normal state at time t;
S5226, integrating the network flow-level throughput real-time data, the link-level packet loss data, the network oscillation duration data, the gateway connectivity data and the normal link proportion data to obtain network performance data corresponding to any unselected network configuration information; the network performance data comprise network flow-level throughput real-time data, link-level packet loss data, network oscillation duration data, gateway connectivity rate data and normal link proportion data;
S53, traversing the network configuration information set, and if the network configuration information set has unselected network configuration information, turning to step S51; if the network configuration information set has no unselected network configuration information, go to step S54;
and S54, integrating all network performance data corresponding to the network configuration information in the network configuration information set to obtain network performance information.
2. The method for analyzing oscillation of a communication network according to claim 1, wherein generating the communication network using a network communication model according to the initial network configuration information comprises:
s31, constructing an initial communication network by utilizing a data plane unit;
S32, carrying out network load configuration on the initial communication network by utilizing a control plane unit according to a preset routing strategy;
S33, configuring the bandwidth and the queue size of a link in an initial communication network by utilizing a traffic density unit, so as to realize the configuration of the initial network capability and obtain the communication network;
The link bandwidth is:
Wherein B i is the bandwidth of link i; an average packet transmission rate for traffic flow f i; alpha is a tolerance coefficient of the bandwidth rate, and the margin of the link bandwidth compared with the normal running state is controlled; f (i) is a set of traffic flows over link i;
The queue size is:
Qi＝(1+β)·max{[Li(t)-Bi],t∈T},β≥0
wherein Q i is the queue size of link i; max { [ L i(t)-Bi ], T epsilon T } is the maximum data residual length of load exceeding the bandwidth size in time T, beta is the tolerance coefficient of the queue size, and the margin degree of the queue size compared with the normal running state is controlled;
the data residual length calculation formula is as follows:
Wherein, L i(t)＞Bi is that the link load L i (t) is larger than the link bandwidth B i at the moment of t, which indicates that data packets remain in the queue, and the value of [ L i(t)-Bi ] is L i(t)-Bi; conversely, [ L i(t)-Bi ] has a value of 0.
3. The method for analyzing the oscillation of the communication network according to claim 2, wherein the network load configuration is performed on the initial communication network by using a control plane unit according to a preset routing policy; comprising the following steps:
S321, calculating a communication flow set in the initial communication network by using a control plane unit to obtain a data packet generation rate of the communication flow; the communication flow characterizes communication data flow between hosts; the host characterizes any terminal in the initial communication network;
s322, processing the link set by using a control plane unit to obtain a link load information set; the set of links characterizes a set of all links in the initial communication network;
the link load information is:
Wherein L i (t) represents link i load information at time t; q i (t-1) is the remaining packets in the queue to which link i corresponds at time t-1, F (i) is the set of traffic flows through link i, The packet arrival rate for the communication flow f k to reach link i at time t;
The arrival rate of the data packet of the communication flow f k reaching the link i at the time t is related to the arrival rate of the data packet at the time t-1, the link bandwidth and the queue size, and is expressed as follows:
where y is the previous link from which the traffic arrives at link i, The packet arrival rate at link y for communication flow f k at time t-1,For the packet arrival rate of all flows t-1 arriving at link y at time, L y (t-1) is the load of link y at time t-1; b y is the bandwidth of link y;
S323, processing the link set by using a control plane unit to obtain a link weight; specifically, the weight w i (t) of link i at time t, said weight w i (t) characterizing the congestion situation of the communication flow as it passes through link i, i.e.
Where B i is the bandwidth of link i and L i (t) is the load size of link i at time t.
4. The method for analyzing the oscillation of the communication network according to claim 1, wherein the processing the communication network by using a network oscillation random model based on the any unselected network configuration information and the network interference information to obtain the oscillation network comprises:
S5211, identifying the link state in the communication network by using a link state classification unit according to any unselected network configuration information and the network interference information to obtain a link state information set; the set of link state information includes state information corresponding to all links in the communication network; the link state information is normal, or, congestion, or overload;
S5212, calculating link state transition in a network by using a link state transition unit to obtain a link state transition probability set; the set of link state transition probabilities includes state transition probabilities corresponding to all links in the communication network;
S5213, updating all links in the communication network by a link state transition unit according to the link state information set and the link state transition probability set to obtain an oscillation network.
5. A communication network concussion analysis system for performing a communication network concussion analysis method as recited in any one of claims 1 to 4, the system comprising: the system comprises an input module, an interference module and a network oscillation analysis module;
the input module is used for inputting initial network configuration information and sending the initial network configuration information to the network oscillation analysis module; the initial network configuration information comprises router information, link information, routing strategy and gateway information;
The interference module is used for generating network interference information and sending the network interference information to the network oscillation analysis module; the network interference information comprises random damage and malicious damage;
The network concussion analysis module comprises a network communication model, a network concussion random model and a network performance evaluation model;
The network communication model is used for constructing a communication network and comprises a data plane unit, a control plane unit, a network configuration unit and a traffic density unit; the data plane unit is used for constructing an initial communication network from a data plane; the control plane unit is used for carrying out network load configuration on the initial communication network from a control plane; the network configuration unit is used for generating different network configurations according to the initial network configuration information; the traffic density unit is used for configuring the bandwidth and the queue size of a link in the communication network;
The network oscillation random model is used for processing the communication network according to the network configuration information and the network interference information and generating an oscillation network, and comprises a link state classification unit and a link state transfer unit; the link state classification unit is used for classifying the link operation conditions in the communication network; the link state transition unit is used for calculating the link state transition probability in the communication network and updating all links in the communication network;
the network performance evaluation model is used for evaluating the performance of the oscillating network and generating network performance data, and comprises a flow-level throughput real-time calculation unit, a link-level packet loss calculation unit, a network oscillation duration calculation unit, a gateway connectivity calculation unit and a normal link proportion calculation unit; the network performance data comprise network flow-level throughput real-time data, link-level packet loss data, network oscillation duration data, gateway connectivity rate data and normal link proportion data; the flow-level throughput real-time calculation unit is used for calculating the network real-time throughput change in the communication network; the link-level packet loss number calculation unit is used for calculating the packet loss number of each link in the communication network; the network concussion duration calculation unit is used for calculating the network concussion duration in the communication network; the gateway connectivity rate calculation unit is used for calculating connectivity rates among gateways in a communication network; the normal link ratio calculating unit is used for calculating the normal link ratio in the communication network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410869863.6A CN118400276B (en) | 2024-07-01 | 2024-07-01 | Communication network oscillation analysis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410869863.6A CN118400276B (en) | 2024-07-01 | 2024-07-01 | Communication network oscillation analysis system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118400276A CN118400276A (en) | 2024-07-26 |
| CN118400276B true CN118400276B (en) | 2024-08-27 |
Family
ID=91988401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410869863.6A Active CN118400276B (en) | 2024-07-01 | 2024-07-01 | Communication network oscillation analysis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118400276B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018179125A1 (en) * | 2017-03-29 | 2018-10-04 | 三菱電機株式会社 | Network configuration information generation method and communication device |
| CN116996160A (en) * | 2023-08-01 | 2023-11-03 | 南京邮电大学 | USRP-based modulation signal interference generation method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3004309B1 (en) * | 2013-04-08 | 2017-03-24 | Thales Sa | DISTRIBUTED METHOD FOR SELECTING A CONFIGURATION IN MOBILE NETWORKS |
| US20230136635A1 (en) * | 2021-10-29 | 2023-05-04 | Hewlett Packard Enterprise Development Lp | Selective formation and maintenance of tunnels within a mesh topology |
| CN114745283B (en) * | 2022-03-01 | 2024-05-17 | 杭州中奥科技有限公司 | Network information protection method and device and electronic equipment |
-
2024
- 2024-07-01 CN CN202410869863.6A patent/CN118400276B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018179125A1 (en) * | 2017-03-29 | 2018-10-04 | 三菱電機株式会社 | Network configuration information generation method and communication device |
| CN116996160A (en) * | 2023-08-01 | 2023-11-03 | 南京邮电大学 | USRP-based modulation signal interference generation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118400276A (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsu et al. | Contra: A programmable system for performance-aware routing | |
| JP6518697B2 (en) | System and method for controlling a network switch using a switch modeling interface on a controller | |
| US7760718B2 (en) | Taxonomy based multiple ant colony optimization approach for routing in mobile ad hoc networks | |
| US8601155B2 (en) | Telemetry stream performance analysis and optimization | |
| US11121984B2 (en) | Routing tables for forwarding packets between switches in a data center network | |
| Muthumanikandan et al. | Link failure recovery using shortest path fast rerouting technique in SDN | |
| US9397924B2 (en) | Method for applying macro-controls onto IP networks using intelligent route indexing | |
| US10873529B2 (en) | Method and apparatus for low latency data center network | |
| US10721295B2 (en) | Popularity-based load-balancing for fog-cloud placement | |
| US11303586B2 (en) | Switching and load balancing techniques in a communication network | |
| Cheng et al. | An in-switch rule caching and replacement algorithm in software defined networks | |
| Baccelli et al. | Scalability of reliable group communication using overlays | |
| JP2021064835A (en) | Network management device and method | |
| Mazloum et al. | A survey on rerouting techniques with P4 programmable data plane switches | |
| Bedi et al. | Mitigating congestion based DoS attacks with an enhanced AQM technique | |
| CN113438182B (en) | Credit-based flow control system and flow control method | |
| CN118400276B (en) | Communication network oscillation analysis system and method | |
| Khoobbakht et al. | Hybrid flow-rule placement method of proactive and reactive in SDNs | |
| KR102537023B1 (en) | Method for controlling network traffic based traffic analysis using AI(artificial intelligence) and apparatus for performing the method | |
| Xu et al. | Novel TCP congestion control scheme and its performance evaluation | |
| Shah | Mitigating TCP incast issue in cloud data centres using software-defined networking (SDN): A survey | |
| Lin et al. | Proactive multipath routing with a predictive mechanism in software‐defined networks | |
| JP2016225729A (en) | Network system, data transfer control method and control device | |
| Davydovskyi et al. | Application of the sliding window mechanism in simulation of computer network loading parameters [J] | |
| Iqbal et al. | VRPR: A New Data Center Protocol for Enhanced Network Performance, Resilience and Recovery |
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 |