Mobile QR Code QR CODE

2024

Acceptance Ratio

21%


  1. (College of General Education, Huanghe Jiaotong University, Jiaozuo, HN 454950, China pandaislidong@163.com)



Small time scale network, Fault tolerant identification, Network interruption fault, Mathematical model, Network data

1. Introduction

Network interruption fault is a common network fault that may cause one or more devices in the network to malfunction, such as switches, routers, terminal devices, etc. [1,2]. Small time scale networks refer to networks with very small time scales, which have high-dimensional, nonlinear and other characteristics during operation. Once a load occurs, it will cause link congestion. Even the entire network may fail, resulting in a decrease in link utilization [3,4]. Therefore, timely detection and fault-tolerant handling of network interruption faults is very important. At present, machine learning based fault tolerant identification methods have become a research hotspot. The application of fault-tolerant identification in network interruption faults can be achieved by analyzing network data. The possible causes of network interruption failures have been identified. Based on these reasons, the network is subjected to fault-tolerant processing. This can better grasp the performance of the network and provide assistance in improving the reliability and security of the network [5,6]. To better address the poor data quality and low model recognition accuracy in small-scale network interruption fault detection, the study innovatively combines small time scales with network fault identification and constructs a mathematical model. The model realizes real-time monitoring of network status and fast identification of faults by integrating time series analysis, machine learning algorithms and complex network theory. The research aims to provide a new judgment path for the study of network interruption faults and improve the ability of fault tolerance identification.

The first part of the study introduces the current research status of fault-tolerant recognition. The second part models small-scale network interruption faults based on fault-tolerant recognition. The third part verifies the performance of the constructed fault-tolerant recognition mathematical model through simulation experiments. The fourth part summarizes the experimental results. The advantages and disadvantages of the research methods are analyzed.

2. Related Work

Fault tolerant recognition is a machine learning technique. It identifies the possible causes of faults by analyzing network data. Based on these reasons, fault tolerant identification of the network is carried out. Fault tolerant identification can better understand the performance of the network and provide support for improving the reliability and security. To better apply fault-tolerant recognition to more industry fields, domestic and foreign scholars have conducted a large amount of research and application. Zare et al. [7] added active fault-tolerant control to construct a predictive control model for controlling and tracking additional faults in discrete-time T-S fuzzy systems. When a fault occurs, the fault-free system serves as the input model. The model is constructed to detect faults. The results indicate that the model constructed using active fault tolerance can effectively detect faults. Engin and Isler [8] constructed a new algorithm based on fault-tolerant detection to address the impact of fault-tolerant network problems on robot repositioning. A new network connection method is used to induce the initial position of the robot. Finally, a uniform random selection was performed. Through extensive simulation experiments, this algorithm can solve localization problems in multi robot systems. Samanta et al. [9] analyzed fault-tolerant faults in mobile services and IoT devices. It has been found that integrating fault-tolerant and mobile edge technology for modeling can better reduce offloading costs. Each uninstallation request is subjected to a requirement analysis. Fault tolerance and edge computing rules are used for calculation. The results indicate that the model can achieve the best approximation ratio. Zhou et al. [10] proposed an adaptive output feedback fault-tolerant controller to investigate the uncertainty of unmodeled actuators and actuator faults. This control consists of three modules: output prediction, adaptation, and control. A low-pass filter is introduced during fault detection to compensate for the uncertainty of the fault-tolerant controller. The results indicate that the feedback fault-tolerant controller can effectively monitor the dynamics of unmodeled controllers and detect faults in a timely manner. Cai et al. [11] studied decentralized fault-tolerant output regulation for actuator faults in multi-agent systems. A fully distributed adaptive fault-tolerant fixed time model has been constructed. This model can utilize fault-tolerant controllers to compensate for execution faults. The results indicate that the fault-tolerant model can effectively solve the fault-tolerant output regulation.

In order to explore the application of neural networks for deep learning in IoT networks, Song et al. [12] introduced DRL into the study of IoT network framework. The study realizes an efficient classification strategy for IoT based on neural networks by combining the strategies of random access and spectrum sharing with DRL. Abid et al. [13] proposed an enhanced IoT Malicious Attack Classification Software for effective detection of malicious attacks in IoT. The study utilizes a malware classification framework combined with integrated machine learning as a way to enhance IoT malware classification. The results show that the research-designed IoT malicious attack classification software, AdaBoost, achieves an accuracy of 96% and also extends the classification software to automated, adaptable detection of large IoT deployments. Zhang et al. [14] optimized fiber optic gyroscopes in order to improve the reliability of their services. A Markov fault-tolerant model was proposed based on optimization. Firstly, the real-time reliability is analyzed by using dynamic parameters. Then the fault tolerance strategy is combined with simulated annealing algorithm. The results indicate that the model can select suitable fiber optic gyroscope nodes to replace faulty nodes, improving the feasibility and effectiveness of fault-tolerant nodes. Deng [15] conducted research on the existing network topology. A new fault-tolerant controller was constructed to correct the collaborative fault-tolerant output regulation in linear heterogeneous systems with actuator faults. The time-varying gain was introduced to evaluate global information. Correction techniques were used to prevent the occurrence of incremental behavior. The results indicate that compared with existing collaborative fault-tolerant output regulation, the new fault-tolerant controller has better regulation ability. Yang et al. [16] constructed an iterative learning fault-tolerant control strategy for the nonlinear problem of actuator failures. Firstly, random faults were obtained. Then, actuator faults and objects were analyzed to calculate the fault control signals. Finally, time weighted techniques were used for policy convergence. The results indicate that the control strategy still has good tracking performance in the event of actuator failure. Liu et al. [17] designed a new fault-tolerant observer to address the low accuracy issue of traditional sliding mode observers in detecting DC motor rotor eccentricity faults. Online identification of interphase inductance parameters is used to adjust the observer in real-time. The results indicate that the new fault-tolerant observer can accurately detect rotor eccentricity faults.

In summary, fault-tolerant recognition technology has great value in practical applications. However, there are still shortcomings in fault-tolerant identification of network interruption faults, such as poor data quality and difficulty in model training. Therefore, based on the summary of the above research, a mathematical model for fault tolerance identification of small time scale network interrupts is constructed, aiming to improve the research and application of fault tolerance identification.

3. Construction of a Mathematical Model for Fault Tolerance Identification of Interruptions based on Small Time Scale Networks

Small time scale networks are a delay based network model. It can run on an hourly time scale. Compared to traditional network models, small time scale networks have higher flexibility and adaptability. It can better cope with changes in network traffic. Therefore, small time scale networks can be used in a variety of application scenarios, such as Network monitoring, packet forwarding and traffic scheduling [18,19].

3.1 Network Interruption Fault Identification based on Small Time Scale Networks

Small time scale network interruption fault identification refers to the fault diagnosis of network systems on a small time scale. By analyzing network system signals, possible faults in the network system are identified. Usually, the characteristics are analyzed mainly from the aspects of small time scale characteristics of signals, characteristics of network interruption signals, network system faults, communication distance and signal transmission. The small time scale characteristics of signals refer to the fact that network signals often have very small time resolution on small time scales, which makes fault diagnosis more difficult. Therefore, the small time scale characteristics of the signal need to be considered for better fault diagnosis. Network interruption signals often have some characteristics, such as sudden rapid changes, continuous slow changes. These features can better achieve fault diagnosis. Network system failure refers to the possibility that a network system may be affected by some failures on a small time scale, such as equipment aging, system updates, human errors, and so on. Therefore, the impact of these faults on the network system should be considered for better fault diagnosis. On a small time scale, communication distance and signal transmission may be subject to some interference, such as noise [20,21,22]. Therefore, the impact of these interferences and factors on communication distance and signal transmission should be considered. Based on bottleneck links, small-scale network fault identification has been studied. Firstly, the case where there is only one bottleneck link in a connected backhaul is considered. The transmission rate of the output link in the transmission direction of a connection is $c_{s} $. The effective bandwidth allocated by a bottleneck link for this connection is $c_{r} $. If $c_{s} > c_{r} $, then the bandwidth allocated to all other links on the return path of this connection is greater than the maximum sum of $c_{s} $ and $c_{r} $. The round-trip link model structure of a single bottleneck link is shown in Fig. 1.

In practical applications, there is more than one bottleneck link on the round-trip path of the connection. The maximum transmission rate of a connection on the output link $j_{0} $ is $c_{0} $. The effective bandwidth allocated by bottleneck link $j_{n} $ for this connection is $c_{n} $. The effective bandwidth allocated by bottleneck links $j_{n} $ and $j_{n-1} $ for this connection is $c_{n-1} > c_{n} $. Any bottleneck free link $j$ between bottleneck links $j_{n-1} $ and must meet the effective bandwidth $c_{j} \ge c_{n-1} $. There are $n$ bottleneck links on one link. The effective bandwidth of this link for this connection is $c_{0} >c_{1}> c_{n} $. From 3.1, it can be seen that the rate of confirming the packet returning to the sender is $c_{n} $. The maximum transmission rate of the sender is the minimum value between $c_{0} $ and $(1+a)c_{n} $. $a$ is a progressive increment. Further assuming $c_{0} > (1+a)c_{n} $, the bottleneck links $j_{i} $ and $j_{i+1} $ on the connected round-trip path satisfy $c_{i} > (1+a)_{cn} > c_{i+1} $. So the number of bottleneck links on the round-trip path of the connection is reduced to $r$, that is, link $j_{i+1} $, $j_{i+2} $, ..., $j_{n} $. Therefore, the round-trip link model structure of the connection is shown in Fig. 2.

Fig. 1. Round-trip link model structure diagram for a single bottleneck link.

../../Resources/ieie/IEIESPC.2025.14.1.45/image1.png

Fig. 2. Architecture diagram of a multi-bottleneck link.

../../Resources/ieie/IEIESPC.2025.14.1.45/image2.png

From the above analysis, it can be seen that when a small-scale network is connected, it can utilize several bottleneck links to achieve communication round-trip. When a long buffer appears on a bottleneck link, the validity value of the buffer is greater than the interrupt failure window. At this point, the average value of the maximum packet in the buffer is the standby state. This buffer is a buffer for multiple bottleneck links. The average value of the maximum group is represented by Formula (1).

(1)
$ {\mathop{q}\limits^{-}} _{\max } =\frac{MAX(A(w_{i} ))}{n} . $

In Formula (1), $A$ represents the average rate of achievement. $w_{i} $ represents the initial value in the connection state. $n$ represents the number of links. $i=1$, $2$, ..., $m-1$.

According to the example of the $i$-th communication return, two links each transmit $w_{i} $ back-to-back data packets, both of which are transmitted to the bottleneck link. The data packets belonging to the transmitting party are transmitted to link 1. Packets belonging to the bottleneck are transmitted to link 2. At this point, the data packet is transmitted to the waiting connection state. The value in buffered state can be calculated using Formula (2).

(2)
$ q_{1}^{i} =w_{i} \left(1-\frac{c_{1} }{(1+a(w_{i} -1)\times c_{n} )} \right). $

In Formula (2), $a$ represents the packet level increment of congestion windows. $c_{n} $ represents effective broadband. On this basis, the average value of the maximum number of groups can be calculated using Formula (3).

(3)
$ {\bar{q}}^{(i)} =\frac{w_{i} }{n} \times \frac{a(w_{i -1} )}{1+a(w_{i -1} )} . $

In Formula (3), $w_{ i-1} $ represents the value at the moment before the connection state. To ensure that the allocation of links meets the requirements, the width of the connection is allocated. The standard value of the distribution is calculated is shown in Formula (4).

(4)
$ f(x)=\frac{1}{c_{\max } } ,~0{\rm }x{\rm }c_{\max } . $

In Formula (4), $c$ represents the bandwidth on the path. Based on Formula (4) analysis, if $n=1$ is present on the communication round-trip path, the minimized bandwidth link must exist on the round-trip path and be effective. If $n=2$, then $c$ represents the effective bandwidth on that path. At this point, the bottleneck bandwidth is shown in Formula (5).

(5)
$ p(c_{2} <c_{1}< 2c_{2} )=\frac{1}{2} \times \frac{2c_{2} -c_{2} }{c_{\max } } . $

In Formula (5), when $0<c_{2} <c{}_{\max } $, it indicates that there must be a bottleneck link. The possibility of becoming a bottleneck link is shown in (6).

(6)
$ p\left\{n=k+1\right\}\\ =p(n=k)\times \frac{1}{2} \left(\frac{2c_{k+1} -c_{2} }{c_{\max } } +\frac{c_{\max } -c_{2} }{c_{\max } }\right). $

In Formula (6), $k$ represents the width rate.

3.2 Construction of a Mathematical Model for Fault Tolerant Identification of Network Interruptions

A reconfigurable service carrying network (RSCN) link fault-tolerant mathematical model has been constructed for identified link failures, which can achieve small-scale network interruption fault repair. Normal communication is ensured in the event of failure. The physical network description of the reconfigurable service bearer network model is completed by a $G^{u} =(N^{u} ,E^{u} ,C^{u} )$ undirected graph. $C^{u} $ represents the carrying capacity, provided by the network. $N^{u} $ represents a physical node. $E^{u} $ represents the set of links. The construction standard for the RSCN model is $G^{r} =(N^{r} ,E^{r} ,C^{r} )$. $N^{r} $ represents a virtual node and belongs to $N^{u} $. $E^{r} $ represents a virtual link and belongs to $E^{u} $. $R^{r} $ represents the demand for bearing capacity. The construction of the RSCN model can be regarded as a mapping process, represented by $G^{s} $. This process is between subsets $G^{r} $ and $G^{u} $. On the basis of meeting the constraint conditions in $G^{r} $, it can be represented by Formula (7).

(7)
$ M:G^{r} =(N^{s} ,E^{s} ,C^{s} )P $

In Formula (7), $N^{s} \subset N^{u} $, $E^{s} \subset E^{u} $. The mathematical model flow commonly used for network fault identification is shown in Fig. 3.

Fig. 3. Mathematical model process commonly used for network fault identification.

../../Resources/ieie/IEIESPC.2025.14.1.45/image3.png

To describe the importance of resources in the network, the resource urgency measure $e$ is introduced into the model. Represented by nodes, many links in a network pass through them. Once $e$ malfunctions, it will cause widespread paralysis of the entire network, greatly affecting its connectivity. Therefore, the influence of node $e$ also needs to be considered. $n_{i} $ represents a node. The degree in $G^{u} $ is represented by $d_{i} $. $NI$ represents the degree of influence vector, belonging to $n_{i} $ and its adjacent nodes. $CF$ represents a resource node that belongs to a physical network. It can be used to describe the degree of segmentation, which is caused by the failure of the remaining network in $n_{i} $. The adjacency matrix is represented by $A(G^{u} )$. $G^{u} $ is a subset. After normalizing the node connectivity, it is the degree of node connectivity. The processing formula is shown in (8).

(8)
$ NCF(n_{i} ) \\ =\left\{\begin{aligned} \frac{NCF(n_{i} )-\min (NCF)}{\max (NCF)-\min (NCF)} ,\\ \hskip 4pc \max (NCF)-\min (NCF)\ne 0,\\ 1, \hskip 3.4pc \max (NCF)-\min (NCF)=0. \end{aligned}\right. $

In Formula (8), $n_{i} $ represents the connectivity of the node. The strength of link connectivity can be expressed by the degree of adjacent point connectivity, as shown in Formula (9).

(9)
$ ECF_{i,j} =\left(\frac{1}{d_{i} } +\frac{1}{d_{j} } \right)/2 . $

In Formula (9), $d_{i} $ represents the specific degree value in the connection. $d_{j} $ represents the connection value in connectivity. When the network is interrupted, the RSCN affected can be described by saturation, as shown in Formula (10).

(10)
$ SF(x)=\left\{\begin{aligned} 0,\;\;\;\;\;\;\;\;\;\;\;\;k=0,\\ (PM_{x} )^{1/k} ,\;x\in N^{u},\\ (PM_{x} )^{1/k} ,\;x\in E^{u}. \end{aligned}\right. $

In Formula (10), $x$ represents the resources in the node and link. $k$ represents the number of nodes. $M_{x} $ represents the assigned resource value. The degree of resource urgency is shown in Formula (11).

(11)
$ \psi (x)=\left\{\begin{aligned} \alpha \cdot NCF(x)+\beta SF(x),\; x\in N^{u} ,\\ \alpha \cdot ECF(x)+\beta SF(x),\; x\in N^{u}. \end{aligned}\right. $

In Formula (11), $\alpha $ represents the regulatory factor 1. $\beta $ represents regulatory factor 2. $\alpha +\beta =1$. $SF(x)$ represents the degree of impact caused by a malfunction. The RSCN link fault-tolerant mathematical model has been constructed. While measuring the construction cost, ensure that the number of RSCNs affected by resource failures is minimized by reducing the occupancy rate of resources with higher urgency. After the requirement decomposition of the model is completed, it is transformed into the sequential solution of each requirement. In $s,t$, the determination of the connection path in $G^{u} $ represents the construction of the model, represented by $V_{s,t} $. The values that need to be met are shown in Formula (12).

(12)
$ \forall c\in V_{s,t} ,~b(c)\ge d_{e}. $

In Formula (12), $b(c)$ represents the bandwidth value in the connecting link. $d_{e} $ represents the measurement value in connectivity. To verify that the constructed attribute model can perform network fault tolerance identification, the constructed mathematical model is compared with random network models and scale-free network models. The results are shown in Fig. 4.

As shown in Fig. 4, the fault tolerance recognition matching rate of the random network model is 93.25%. The fault-tolerant recognition matching rate of the mathematical model is 96.72%. The fault tolerance recognition matching rate of the scale-free network model is 89.97%. The fault-tolerant recognition matching rate of the mathematical model is significantly higher than the other two models, indicating that the constructed mathematical model can be used for experiments. The link recovery mechanism is used to map and migrate terminal failed links. Based on the goal of minimizing adjustment costs, fault-tolerant analysis of interrupt failures is implemented. The mathematical model construction process for fault tolerance identification of network interruption faults is shown in Fig. 5.

Fig. 4. Matching of the three models.

../../Resources/ieie/IEIESPC.2025.14.1.45/image4.png

Fig. 5. Mathematical construction process for fault-tolerant identification of network outages based on small time scales.

../../Resources/ieie/IEIESPC.2025.14.1.45/image5.png

4. Performance Analysis of a Mathematical Model based on Fault Tolerance Identification

To analyze the actual performance of the mathematical model built by the research, the performance comparison experiment is conducted with Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Deep Neural Networks (DNN).

4.1 Performance Analysis of Mathematical Models based on Fault Tolerance Identification

The fault-tolerant performance of the mathematical model in the case of interrupt faults with different window sizes was tested. The accuracy, loss rate accuracy, and absolute error of the four methods are used as evaluation indicators. Fig. 6 shows the accuracy and loss rate results of these four methods.

Fig. 6. Comparison of the accuracy and loss rate results of the four methods.

../../Resources/ieie/IEIESPC.2025.14.1.45/image6.png

Fig. 7. Accuracy and mean absolute error results of the four methods.

../../Resources/ieie/IEIESPC.2025.14.1.45/image7.png

As shown in Fig. 6, as the number of iterations increases, the accuracy of all four methods shows an upward trend. The loss rates of all four methods show a decreasing trend. The final accuracy of the mathematical model proposed in the study is 90.9%. The final accuracy values of DNN, RNN, and CNN are 87.35%, 83.71%, and 82.46%, respectively. The loss rate of the mathematical model proposed in the study is 2.43%. The loss rates of DNN, RNN, and CNN are 2.47%, 2.49%, and 2.53%, respectively. This indicates that judging from the two dimensions of accuracy and loss rate, the mathematical model proposed in the study performs better than the comparison method. Fig. 7 shows the accuracy and Mean absolute error results of the four methods.

Fig. 7(a) shows the accuracy comparison results of the four methods. As shown in Fig. 7(a), with the increase of iteration, the accuracy of all four methods shows an upward trend. The final accuracy of the mathematical model proposed in the study is 91.53%. The final accuracy of DNN, RNN, and CNN were 86.26%, 81.96%, and 78.81%, respectively. Fig. 7(b) shows the comparison results of Mean absolute error of the four methods. It can be seen from Fig. 7(b) that with the increase of iteration, the Mean absolute error of the four methods shows a downward trend. The Mean absolute error of the proposed mathematical model is 0.0004. The Mean absolute error values of DNN, RNN and CNN are 0.008, 0.0061 and 0.0069 respectively. This shows that the performance of the mathematical model proposed in the study is also better than the comparison method from the perspective of accuracy and Mean absolute error. The running time of the four methods is compared. In order to prevent the occurrence of accidental errors, the running time of the four methods is Threefold repetition repeated experiments. The running time results of the four methods are shown in Table 1.

It can be seen from Table 1 that in the threefold repetition experiments, the proposed mathematical model has the lowest time consumption. And the average time consumption of the method in the three repeated experiments is 232 seconds. The average time consumption for DNN, RNN, and CNN is 280 s, 271 s, and 291 s. This indicates that the running time of the mathematical model is less than the other three methods. Therefore, from the perspective of running time, the proposed mathematical model performs better than the comparison method. Based on the above, the comparison results from multiple dimensions indicate that the mathematical model has high stability and feasibility.

Table 1. Comparison results of the running time of the four methods.

Number of experiments

Algorithm

Running time (s)

First comparative experiment

IGRA algorithm

242

RANSAC algorithm

280

NS algorithm

269

DS algorithm

290

Second comparative experiment

IGRA algorithm

238

RANSAC algorithm

279

NS algorithm

270

DS algorithm

288

Third comparative experiment

IGRA algorithm

239

RANSAC algorithm

277

NS algorithm

272

DS algorithm

293

4.2 Application Analysis of Mathematical Models based on Fault Tolerance Identification

In order to test the application performance and effectiveness of the research and construction model, a scalable noxim simulator was used to simulate small-scale networks to complete simulation testing. During testing, random network mode and hotspot mode are used as comparative methods to determine the application effectiveness of the mathematical model.

From Fig. 8(a), it can be seen that in random mode, as the interrupt fault window increases, there is no increase in network band and number. The network status is in a small band state. In hotspot mode, the situation that occurs when the interrupt fault window increases is roughly the same as in random mode, with small fluctuations. But they all meet the design requirements. This indicates that the constructed mathematical model has good fault-tolerant performance in both types of networks. From Fig. 8(b), it can be seen that in the random model, the success rate of the mathematical model shows a decreasing trend. The overall success rate is 89.63% and will eventually stabilize.

In the hotspot model, the success rate of the mathematical model decreases first and then slightly increases as the proportion increases. The successful operation rate when it finally stabilizes is 81.95%. This indicates that the constructed attribute model can meet the design requirements. In order to further verify the fault-tolerant effect of the mathematical model, interrupt faults in small-scale time networks are simulated in random mode and hotspot mode. The results are shown in Fig. 9.

Fig. 8. Fault tolerance and long-term operational success test results.

../../Resources/ieie/IEIESPC.2025.14.1.45/image8.png

Fig. 9. Node connectivity test

../../Resources/ieie/IEIESPC.2025.14.1.45/image9.png

Fig. 10. Average link utilization and average packet energy consumption tests

../../Resources/ieie/IEIESPC.2025.14.1.45/image10.png

As shown in Fig. 9, in the event of a node failure, it is mapped to achieve link migration. It can also achieve effective connection and information transmission between neighboring and failed nodes. The mapping results of at least two adjacent nodes near each failed node are ensured. The higher the utilization rate of physical links, the higher the effectiveness value of network resource utilization, indicating better fault tolerance performance of the system. This indicates that there is a correlation between the utilization of physical links and fault tolerant identification. In order to further verify the fault-tolerant ability of the mathematical model, the link utilization rate and average energy consumption of data packets are used to determine the effectiveness of fault-tolerant recognition. The results are shown in Fig. 10.

As shown in Fig. 10(a), as the ratio continues to increase, the utilization rate of the links in both modes fluctuates. The average utilization rate in random mode is 87.53%. The average utilization rate in hotspot mode is 88.21%. The difference in fault tolerance utilization between the two is very small, and both are above 85%. This indicates that the mathematical model has good fault-tolerant recognition rate in both modes. As shown in Fig. 10(b), after applying the mathematical model constructed in the research, the number of interrupts increases in random mode. The average energy consumption of data packets is 0.67. When the mathematical model is not used, the average energy consumption of the data packet is 0.71. After using the mathematical model, the average energy consumption of data packets in hotspot mode is 0.49.

The average energy consumption of the data packet before using the mathematical model is 0.77. This indicates that the average energy consumption of the data packet significantly decreases after using the mathematical model. Using mathematical models under the same conditions can reduce energy consumption and complete data transmission. To verify the recognition and classification ability of mathematical models for different network interruption faults, two modes were applied to dataset testing. A total of 6 types of network interruption data were used in the dataset, as shown in Fig. 11. The patterns of different shapes and colors in the figure represent different types of network interruption faults. The same type of network interruption fault is the same. Fig. 11(a) shows the classification effect of random patterns. Fig. 11(b) shows the classification effect of hotspot patterns.

Fig. 11. Comparison of network outage fault classification in two modes.

../../Resources/ieie/IEIESPC.2025.14.1.45/image11.png

The classification of network interruption fault data can be used to determine the fault tolerance ability of mathematical models. As shown in the figure, both modes can recognize and classify six types of network interruption data. However, there are differences in the classification and location labeling of the same network interruption fault type between the two. This indicates that there are differences in the judgment of fault-tolerant nodes between the two modes in the constructed mathematical models. There are still differences in the number of scatter points used to identify and classify faults, but the difference is not significant. This indicates that both models can effectively classify interrupt networks in the constructed mathematical models, and the results are very good. The reliability of the constructed mathematical model has been verified.

Fig. 12. Comparison of fault tolerance identification results for small and medium time scale networks in transmission control protocol.

../../Resources/ieie/IEIESPC.2025.14.1.45/image12.png

In order to further validate the performance of the research constructed model, the study applies it to the Internet router buffer design platform for performance verification. One of the goals of the Internet router switching design is to ensure that the link utilization can reach 100%, however, the emergence of small time scale networks can greatly affect the link utilization, in order to validate the performance of the model in the small time scale network fault tolerance identification, the study is conducted in the Internet router buffer design platform for fault tolerance fault identification. The comparison results of small time scale network fault tolerance identification for transmission control protocols are shown in Fig. 12.

As analyzed in Fig. 12, in the Internet router buffer 500 M throughput buffer platform, the throughput designed for 500 M can only provide about 253 M network bandwidth before the fault-tolerant fault identification process. After the introduction of fault-tolerant fault identification model, the overall bandwidth are significantly improved, and can provide about 436 M network bandwidth. Although there is still a gap with the real value, the bandwidth is significantly improved compared to the bandwidth when there is a fault. This indicates that the mathematical model constructed in the study for fault tolerance identification of network outages at small time scales can significantly improve the bandwidth flux in the fault tolerance of the Internet router buffer design platform, and provide practical results for the enhancement of network traffic.

5. Discussion

Through the analysis of the above content, it is found that the research for small time scale network interruption fault fault tolerance identification, the construction of the corresponding mathematical model is the key to ensure the stability of the network. In the process of model construction, it is necessary to deeply analyze the characteristics of network interruption faults, including the time scale of their occurrence, the propagation mode of the fault and the influence range. The model should have the ability to respond quickly and identify accurately in order to intervene and repair effectively at the early stage of the fault. In addition, it is crucial for the model to be fault-tolerant, which is able to maintain a high recognition accuracy despite unstable network states or missing data. To this end, advanced machine learning algorithms can be used to train models with strong fault tolerance by combining network topology and historical fault data. Through continuous model optimization and testing, the performance of the model can be improved to provide more reliable mathematical support for fault-tolerant identification of actual network outage faults.

6. Conclusion

With the rapid increase of network traffic, the identification and detection requirements of network interruption are becoming higher and higher. To address the problems of difficult data recognition and low model accuracy in traditional network interrupt fault detection, a small time scale network interrupt fault tolerance recognition mathematical model is constructed. By constructing a mathematical model for fault tolerance identification of network interrupts, the performance of the model is verified through comparative algorithms and simulation experiments. The experimental results show that the accuracy of the mathematical model is 90.9%. The final accuracy of DNN, RNN, and CNN are 87.35%, 83.71%, and 82.46%, respectively. The loss rate of the mathematical model is 2.43%. The loss rates of DNN, RNN, and CNN are 2.47%, 2.49%, and 2.53%, respectively. This indicates that the proposed mathematical model outperforms the comparison method in terms of accuracy and loss rate. After applying the mathematical model to random mode and hotspot mode, the average energy consumption of the data packet was 0.67 and 0.49, respectively. Compared to the average energy consumption before application, there has been a decrease. The performance of the mathematical model has been verified. But there are still shortcomings in the research. There are few applications for different types of network interruption faults. The next step is to identify more network interruption faults with fault tolerance.

REFERENCES

1 
M. D. Fabiani and B. Behlendorf, ``Cumulative disruptions: Interdependency and commitment escalation as mechanisms of illicit network failure,'' Global Crime, vol. 22, no. 1, pp. 22-50, 2021.DOI
2 
R. Nakamura and N. Kamiyama, ``Content availability at network failure in information-centric networking,'' IEEE Transactions on Network and Service Management, vol. 18, no. 3, pp. 3889-3899, 2021.DOI
3 
R. Lent, ``A cognitive anycast routing method for delay-tolerant networks,'' Network, vol. 1, no. 2, pp. 116-131, 2021.DOI
4 
N. Khan, R. Bin Salleh, I. Ali, Z. Khan, and R. Bin, ``Enabling reach ability across multiple domains without controller synchronization in SDN,'' CMC-Computers Materials & Continua, vol. 69, no. 1, pp. 945-965, 2021.DOI
5 
P. K. Thiruvasagam, A. Chakraborty, and C. S. R. Murthy, ``Resilient and latency-aware orchestration of network slices using multi-connectivity in MEC-enabled 5G networks,'' IEEE Transactions on Network and Service Management, vol. 18, no. 3, pp. 2502-2514, 2021.DOI
6 
H. Shi, L. Zhang, X. Zuo, Q. Wu, H. Li, and Y. Cui, ``Multipath deadline-aware transport proxy for space network,'' IEEE Internet Computing, vol. 25, no. 6, pp. 51-57, 2021.DOI
7 
Zare, P. Setoodeh, and M. H. Asemani, ``Fault-tolerant tracking control of discrete-time TS fuzzy systems with input constraint,'' IEEE Transactions on Fuzzy Systems, vol. 30, no. 6, pp. 1914-1928, 2021.DOI
8 
K. S. Engin and V. Isler, ``Establishing fault-tolerant connectivity of mobile robot networks,'' IEEE Transactions on Control of Network Systems, vol. 8, no. 2, pp. 667-677, 2021.DOI
9 
Samanta, F. Esposito, and T. G. Nguyen, ``Fault-tolerant mechanism for edge-based IoT networks with demand uncertainty,'' IEEE Internet of Things Journal, vol. 8, no. 23, pp. 16963-16971, 2021.DOI
10 
Y. Zhou, H. Liu, and H. Guo, ``L1 adaptive output-feedback fault-tolerant control for uncertain nonlinear systems subject to unmodeled actuator dynamics and faults,'' Transactions of the Institute of Measurement and Control, vol. 44, no. 11, pp. 2177-2192, 2022.DOI
11 
Y. Cai, H. Zhang, J. Zhang, S. Sun, and Q. He, ``Distributed fault-tolerant output regulation for heterogeneous linear multi-agent systems under actuator faults,'' Journal of the Franklin Institute, vol. 358, no. 7, pp. 3303-3331, 2021.DOI
12 
H. Song, J. Bai, Y. Yi, J. Wu, and L. Liu, ``Artificial intelligence enabled internet of things: network architecture and spectrum access,'' IEEE Computational Intelligence Magazine, vol. 15, no. 1, pp. 44-51, Feb. 2020.DOI
13 
Y .A. Abid, J. S. Wu, M. Farhan, and T. Ahmad, ``ECMT framework for internet of things: an integrative approach employing hybridized machine learning methodologies,'' IEEE Internet of Things Journal, vol. 11, no. 5, pp. 5867-5886, Sep, 2023.DOI
14 
Zhang, Y. Chen, M. Zhou, G. Xu, and A. Abusorrah, ``A fault-tolerant model for performance optimization of a fog computing system,'' IEEE Internet of Things Journal, vol. 9, no. 3, pp. 1725-1736, 2021.DOI
15 
C. Deng, ``Cooperative fault-tolerant output regulation of linear heterogeneous multiagent systems under directed network topology,'' IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 51, no. 8, pp. 4773-4781, 2019.DOI
16 
X. Yang, X. Ruan, and Y. Geng, ``Iterative learning fault-tolerant control for discrete-time nonlinear systems subject to stochastic actuator faults,'' Transactions of the Institute of Measurement and Control, vol. 44, no. 10, pp. 2012-2023, 2022.DOI
17 
S. Liu, K. Xing, Y. Lin, and W. Dong, ``Design of fault-tolerant observer for brushless DC motor under rotor eccentricity fault,'' International Journal of Modelling, Identification and Control, vol. 39, no. 1, pp. 11-18, 2021.DOI
18 
M. H. Abobeih, Y. Wang, J. Randall, J. H. Loenen, C. E. Bradley, M. Markham, D. J. Twitchen, B. M. Terhal, and T. H. Taminiau, ``Fault-tolerant operation of a logical qubit in a diamond quantum processor,'' Nature, vol. 606, no. 7916, pp. 884-889, 2022.DOI
19 
S. Li, Y. Qin, Z. Jiang, and W. Yang, ``Efficient communication scheduling for parameter synchronization of DML in data center networks,'' IEEE Transactions on Network Science and Engineering, vol. 9, no. 4, pp. 1970-1985, 2021.DOI
20 
X. Zhang, S. Liu, and H. Wang, ``Personalized learning path recommendation for e-learning based on knowledge graph and graph convolutional network,'' International Journal of Software Engineering and Knowledge Engineering, vol. 33, no. 1, pp. 109-131, 2023.DOI
21 
S. Choudhuri, S. Adeniy, and A. Sen, ``Distribution alignment using complement entropy objective and adaptive consensus-based label refinement for partial domain adaptation,'' Artificial Intelligence and Applications, vol. 1, no. 1, pp. 43-51, 2023.DOI
22 
J. Han, K. Xue, Y. Xing, J. Li, and G. Xue, ``Leveraging coupled BBR and adaptive packet scheduling to boost MPTCP,'' IEEE Transactions on Wireless Communications, vol. 20, no. 11, pp. 7555-7567, 2021.DOI
Xiaodong Li
../../Resources/ieie/IEIESPC.2025.14.1.45/author1.png

Xiaodong Li received his bachelor of science degree in applied mathematics from Zhengzhou University, Zhengzhou, China, in 2002. He works at Huanghe Jiaotong University. His current research interests include Applied Mathematics, Mathematics Teaching.