=Paper=
{{Paper
|id=Vol-2922/paper002
|storemode=property
|title=Modeling the processes of predicting the characterictics of faults in information systems
|pdfUrl=https://ceur-ws.org/Vol-2922/paper002.pdf
|volume=Vol-2922
|authors=Igor Lvovich,Yakov Lvovich,Andrey Preobrazhenskiy,Yuriy Preobrazhenskiy,Oleg Choporov
}}
==Modeling the processes of predicting the characterictics of faults in information systems==
https://ceur-ws.org/Vol-2922/paper002.pdf
Modeling the processes of predicting the characterictics
of faults in information systems*
Igor Lvovich1[0000-0003-4236-6863], Yakov Lvovich2, Andrey Preobrazhenskiy1[0000-0003-4236-
6863]
, Yuriy Preobrazhenskiy1 and Oleg Choporov2[0000-0002-3176-499X]
1
Voronezh institute of high technologies, 73a, Lenina Street, Voronezh, 394043, Russian Fed-
eration
2
Voronezh state technical university, 14, Moscow Avenue, Voronezh, 394026, Russian Fed-
eration
komkovvivt@yandex.ru
Abstract. In connection with the widespread use of information systems in
various activities, an urgent problem is to estimate their characteristics. One of
the possible types of characteristics can be various failures and malfunctions. In
this paper, to estimate the characteristics of malfunctions in information sys-
tems, it is proposed to use the apparatus of neural networks. In this paper, the
process of dividing the initial set of objects into homogeneous groups is carried
out. This is due to the fact that the forecasting accuracy will be improved before
the models are formed. For an algorithm that makes it possible to form predic-
tive models, the main steps that are included in it are indicated. The algorithm
for learning a neural network is given. The illustration of a block diagram of a
neural network is shown. The results of verification of models that allow pre-
dicting failure of communication devices are demonstrated. The investigation
can be useful for characterizing a wide class of information systems.
Keywords: Information system, predicting, model, neural network, fault.
1 Introduction
At present, information systems in their structure and characteristics of functioning
belong to the class of complex systems. In this regard, when solving various problems
of predicting their parameters, it is necessary to rely on the methods of system analy-
sis. Among the various processes taking place in information systems [1-2], the oc-
currence of various malfunctions can be noted. They need to be predicted.
The aim of this paper is to develop an approach within which it is possible to pre-
dict the characteristics associated with malfunctions in information systems.
*
Copyright c 2021 for this paper by its authors. Use permitted under Creative Commons License Attribu-
tion 4.0 International (CC BY 4.0).
2 The use of neural network modeling in the course of
forecasting the processes of observation of faults in
information systems
Faults in information systems are of a heterogeneous nature [3]. This determines that
in order to eliminate them, it is important to focus on an individual approach. The
appropriate steps are selected during the fault analysis. We must define the specifics
of the control system [4]. It is based on two basic processes. In the first, we determine
the state of the information system. In the second, optimal influences are developed
for this state. When a troubleshooting tactic is selected, then predicting how the moni-
tored parameters will change can be considered an important step. In this case, predic-
tive models are used [5-6].
Methods of active and passive experiment provide opportunities in order to obtain
mathematical descriptions. For many cases, approaches that are associated with re-
gression analysis are used. We can take into account the specifics of the problem un-
der consideration. In the course of the modeling processes, we use a passive experi-
ment. It requires consideration of experimental and archival information. There are
still opportunities to observe the ongoing process. An active experiment can also be
considered. Then it is necessary to rely on the method of directed survey of special-
ists.
How will the controlled indicator depend on each of the analyzed attribute-factors?
Regression predictive models are often effective.
This is due to the fact that on their basis it is possible to visually demonstrate the
necessary dependencies. But on their basis, there is no opportunity to carry out the
identification of hidden, "confusing" dependencies. When considering this class of
problems, it is of interest to use neural network models.
When using them, it is possible to create more efficient predictive models in com-
parison with the approaches in traditional statistical modeling. Spaces can be charac-
terized by large dimensions [7]. This is due to the large number of telecommunication
facilities in modern networks. Then approaches based on regression analysis in
mathematical modeling will lead to the emergence of artificial constructions.
It is necessary to ensure the operability of information and telecommunication sys-
tems. At the same time, the accuracy of the approximation, which is obtained by the
methods of neural networks, will increase noticeably.
Information and telecommunication systems are formed in different ways. In the
course of solving problems in the field of information technology, in almost all cases,
there will be several ways of solving. From the point of view of practical implementa-
tion, their answer is characterized by "fuzziness" [8-9].
That is, during the solution, it is necessary to analyze certain intervals, within
which the parameters of interest will be located. A similar mechanism can be noted in
this when compared with the way in which the result is demonstrated based on neural
networks. How can the values of the parameters of systems influence their behavior?
We can only indicate an approximate set of such conditions, which will be the
most important. The number of parameters under study can be quite large. In practice,
some of the conditions are ignored. Why the answer will be rough? This is due to the
fact that it will be characterized by inaccuracy. Another difficulty is related to the fact
that we cannot record the algorithm for determining the answer in a precise way.
On the other hand, training a neural network can be carried out based on those ex-
amples that are quickly collected. If a neurosimulation process is underway, then
there is no need to explicitly highlight clear rules. This is due to the fact that. instead
of forming an appropriate algorithm of work, we can carry out the process of "train-
ing" the neural network using known statistics.
Let's show some conditions under which neural networks are formed. Suppose
there is some set of input-output vector pairs.
There is a certain condition for them. It consists of arbitrary dimension {(Xk, Yk),
k=1...K}. In such cases, there will be a two-layer homogeneous neural network. It
has the general properties of neural networks. It highlights sigmoidal transfer func-
tions. There is one more characteristic. It has serial connections [10, 11]. There are a
finite number of neurons. Such a network is useful for solving a wide range of practi-
cal problems. Due to the use of such a neural network for each input vector Xk, the
corresponding output vector Yk will be formed.
A similar model is used in data processing. We need to carry out the process of
forming models for forecasting. In a network [12, 13], in general, there can be a dif-
ferent number of layers. To solve our problem, we will consider a network that will be
characterized by several layers. It will also be homogeneous
Sigmoidal transfer functions can be written in different ways:
1
f(s) (1)
1 e 2s
Formula (1) is written in general form.
In the above formula, s - is considered as the output of a neuron adder, - is con-
sidered as a parameter,
2. Rational sigmoid:
s
f(s) (2)
s
Functions (1) and (2) will be monotonically increasing. Their peculiarity lies in the
fact that they are characterized by nonzero derivatives over the entire domain of defi-
nition. This is important from the point of view of improving the accuracy in calcula-
tions.
These characteristics ensure the proper functioning and training of the network. It
is important to make the choice of sigmoidal transfer functions. The most efficient
transfer function is the rational sigmoid.
The structure of the network is selected during research. It will influence the accu-
racy characteristics of neural network models. Another characteristic is the number of
neurons. For the hidden layers of a three-layer network, to assess the number of neu-
rons, we will consider the specified expression:
NyN p
1 log 2 N p
N w N y
Np
N
1 N x N y 1 N y
(3)
x
It is used for a large number of practical cases.
In the specified expression, Ny is considered as the dimension of the output signal,
Np - is considered as the number of elements that are included in the training sam-
ple,
Nx - shows the dimension that will correspond to the input signal.
The “back propagation” algorithm can be considered effective from the point of
view of its practical application when training neural networks. The features of a mul-
tilayer network are described by the following expressions:
N m i
s i m wi m i mi y i mi b i m , i m 1,2,..., N m , m 1,2,..., L (4)
i mi 1
y i f s i m , i m 1,2,..., N m , m 1,2,..., L
m
(5)
In the specified expression, f - is the activation function, y - denotes the output of
the neuron, s - denotes the output of the adder, b - shows the bias value, w - shows the
weight of the connection, i - shows the number of the neuron, N - shows the number
of neurons that are in the layer, L - shows the number of layers, m - shows the layer
number. During the process of training the network, we can indicate the following
basic stages:
1) The process of initializing the network is in progress. That is, the initial values
of the parameters are set. Then there will be assignment of weights and biases of the
network of small random values over certain ranges. A similar assignment of parame-
ters can be implemented for a wide range of practical tasks [14-15].
2) The element in the training sample is determined: (, ). For the current inputs (x0, x1 ... xN-1), the difference should be ensured for all
elements that are in the training set. There may be different options for implementa-
tion. If a multilayer perceptron is used as a classifier, then the output signal (d0, d1 ...
dN-1), which we should receive, is formed on the basis of zeros.
There is a peculiarity. In this case, there is one single element. It is considered as a
classifier. It belongs to the class to which the considered input signal will belong.
3) The output in question is calculated. It is required for analysis. In this case, we
are based on how the traditional scheme will be taken into account, on the basis of
which the multilayer neural network works.
4) It is required to prepare the neural network for work. Synaptic weights are ad-
justed. This can be done in different ways.
This process uses a recursive algorithm. It consists of several steps. At the first
step, we apply it to the output neurons of the network. This takes a little time. After
that, in the opposite direction, we will go through the network to the first layer. The
synaptic balance adjustment process takes place based on what is indicated in the
formula:
wij ( t 1 ) wij ( t ) r g j x' j (6)
In the specified expression, gj - is considered as the value of the error for neuron j,
r - shows the value of the learning step, xi' - is considered as the output of the neuron
for the i or i-th element of the input signal, wij - is the weight of the neuron i or the
element that is associated with input signal i which refers to neuron j for time t.
When the neuron that has the number j will be on the last layer, then
g j y j ( 1 y j )( d j y j ) , (7)
In the above expression, yj is considered as the current output of neuron j, dj is con-
sidered as the desired output of neuron j.
If the neuron that has the number j belongs to one of the layers that is not the last,
then
g j x' j (1 x' j ) g k w jk , (8)
In the above expression, k will change in accordance with all neurons in the layer,
whose numbers will be one more than for the one to which neuron j will correspond.
We use a similar approach in order to adjust the external displacements of neurons
b. In order to train neural networks when building models for forecasting, we propose
to use a modified backpropagation algorithm (Fig. 1). In the course of its formation,
such an inertial ratio was used, which makes it possible to find the step size for each
of the iterations
wij t 1 wij t r g j x' j wij t wij t 1 , (9)
In the above expression, - is considered as a coefficient of inertia, 01.
The learning rate is significantly reduced due to this modification.
Making an optimal choice in terms of control actions is an important step in pre-
dicting a change parameters in information systems [16].
The process of dividing the initial set of objects into homogeneous groups is in
progress. Then the accuracy in forecasting is increased before the models are formed
[17]. The main approach is based on the fact that we apply the partition by bioho-
mogeneous components [18]. There can also be a partition using the methods of clus-
ter analysis. The construction of models for forecasting occurs within each of the
groups in a separate way. If there are difficulties in the course of creating homogene-
ous groups, then indicators that take into account the fact that malfunctions in infor-
mation systems are heterogeneous will be included in the generalized predictive
model. They will be considered as additional dependent variables. In order to select
the most effective troubleshooting tactics, for predictive models, the dependent vari-
ables are considered as control values for the time that corresponds to the end of the
observation [19]. If independent variables are considered, then they will correspond to
the values of the same indicators before the start of observation. The algorithm for
generating predictive models contains the following steps.
1. The set of indicators X i i 1, N is determined using a survey of experts. On
their basis, it is possible to fully identify the state of information systems. In addition,
one can take into account their individual inhomogeneities.
2. We indicate one or more monitored indicators Y j
j 1, M . The way they
change over time has an impact on the assessment of the state of the information sys-
tem. On their basis, we can consider the features of the effectiveness of management
influences.
3. We filter information so that reliable measurements are selected.
4. Parametric redundancy is eliminated. This is due to the choice of the optimal
feature space.
5. The structure is selected for the model [20-21].
6. Model building in progress.
7. The model is tested in terms of how adequate it will be. If it is confirmed that the
model will be adequate, then the algorithm will be terminated. Otherwise, we can
complicate the model. Then we will go to step 5.
Fig. 1. Algorithm for learning a neural network.
Fig. 2. Illustration of a block diagram of a neural network.
Otherwise, adjustments should be made to the original sample. In such cases, it can
provide growth in its volume. There will be a reduction in the number of unreliable
measurements. In the course of modeling the development of malfunctions caused by
the failure of communication devices, 5 neural network models were formed.
For some of x from, the information processing time is used as a parameter t, for
others, the duration of the fault is considered.
From an architectural point of view, the created neural networks will be multi-
layered. The formed neural networks will contain up to 30 neurons. They are on 3
layers. They will be as follows: input, internal and output.
The specified number of neurons will be sufficient to fully train neural networks to
simulate the failure of communication devices. Moreover, there is no redundancy in
the number of neurons. In such cases, the relationship between input and output pa-
rameters can be shown very accurately. Neural networks will not carry out a simple
process of memorizing by examples in a training set. Figure 2 illustrates a block dia-
gram of one of the resulting models. It corresponds to the failure of the switches.
3 Results of modeling
The process of learning neural networks is underway. Then the backpropagation algo-
rithm will be implemented. We consider the multicriteria optimization problem for
the backpropagation method as a set of single-criterion ones. For each of the itera-
tions, the values of the network parameters are changed.
They will improve on only one example in the training set. Due to the application
of this approach, we significantly reduce the speed when learning. In order to increase
the convergence rate during the training of the neural network, we used a modified
backpropagation algorithm. In the course of its practical implementation, the step size
for each iteration will be determined using the inertial ratio.
We carried out the neural network training process on the basis of training samples.
They were in the database. As a result of training, all neural networks created during
the study turned out with a sufficient level of accuracy.
To verify the obtained models, we used control samples. For each of them, at least
10 objects were included that were not included in the main group.
To assess the effectiveness of the models, we calculated such indicators as the av-
erage and maximum error of the output value. The results of testing the generated
models for forecasting are shown in table. 1.
Table 1. Results of verification of models that allow predicting failure of communication
devices.
Head 1 Volume of Samples Samples Average Maximum Error
Error
Voltage instability in
the electrical net- 12 7.34 10.00
work of level 1
Voltage instability in
the electrical net- 10 7.55 10.00
work of level 2
Failure of the first
level communicators 19 10.43 45.98
Failure of the second
level communicators 13 7.06 34.99
Failure of the third
communicators level 10 6.48 9.95
After the forecast is obtained, it is necessary to choose an adequate troubleshooting
scheme
4 Conclusion
The paper shows the possibility of solving a problem aimed at predicting faults in
information systems. An algorithm for learning a neural network is developed, an
illustration of a structural diagram of a neural network is given. To verify the obtained
models, we used control samples. For each of them, at least 10 objects were included
that were not included in the main group. To assess the effectiveness of the models,
we calculated such indicators as the average and maximum error of the output value.
Results of verification of models that make it possible to predict the failure of com-
munication devices
References
1. Stankovic, J.A.: Research directions for the internet of things. IEEE Internet of Things
Journal, 1, 3-9 (2014).
2. Rios, L.M. and Sahinidis, N.V. Derivative-free optimization: a review of algorithms and
comparison of software implementations. Journal of Global Optimization, 54, 1247-1293
(2013).
3. Lutakamale, A.S., Kaijage, S. Wildfire Monitoring and Detection System Using Wireless
Sensor Network: A Case Study of Tanzania. Wireless Sensor Networkl 9, 274-289 (2017).
4. Odu, G.O. and Charles-Owaba, O.E. Review of Multi-criteria Optimization Methods.
Theory and Applicationsl 3, 1-14 (2013).
5. Shah A., Ghahramani Z. Parallel predictive entropy search for batch global optimization of
expensive objective functions. Advances in Neural Information Processing Systems, 3330-
3338 (2015).
6. Morais, H., Kádár, P., Faria, P., Vale, Z.A. and Khodr, H.M. Optimal Scheduling of a
Renewable Micro-Grid in an Isolated Load Area Using Mixed-Integer Linear
Programming. Elsevier Editorial System(tm) for Renewable Energy Magazine, 35(1), 151-
156 (2010).
7. Orlova, D.E. Stability of solutions in ensuring the functioning of organizational and
technical systems. Modeling, Optimization and Information Technologies, 6(1), 325-336
(2018).
8. Talluri, S., Kim, M.K. and Schoenherr, T. The relationship between operating efficiency
and service quality: are they compatible? Int. J Prod Res, 51, 2548-2567 (2013).
9. Groefsema, H., Beest, N.R.T.P. Design-time compliance of service compositions in
dynamic service environments. Int. Conf. on Service Oriented Computing & Applications,
108-15 (2015).
10. Lvovich, I.Ya., Lvovich, Ya.E., Preobrazhenskiy, A.P., Preobrazhenskiy, Yu.P.,
Choporov, O.N. Modelling of information systems with increased efficiency with
application of optimization-expert evaluation. Journal of Physics: Conf. Ser. Krasnoyarsk
Science and Technology City Hall of the Russian Union of Scientific and Engineering
Associations; Polytechnical Institute of Siberian Federal University. Bristol, United
Kingdom, 33079 (2019).
11. Yao, Y. and Chen, J. Global optimization of a central air-conditioning system using
decomposition-coordination method. Energy and Buildings, 5, 570-583 (2010).
12. Lvovich, I., Preobrazhenskiy, A., Preobrazhenskiy, Y., Lvovich, Y., Choporov, O.
Managing developing internet of things systems based on models and algorithms of multi-
alternative aggregation Int. Seminar on Electron Devices Design and Production, SED-
2019 – Proceedings, 8798413 (2019).
13. Akyildiz, I.F., Wang, P., Lin, S.C. SoftAir: A software defined networking architecture for
5G wireless systems. Computer Networks, 85, 1–18 (2015).
14. Han, B., et al. Network function virtualization: Challenges and opportunities for
innovations. Communications Magazine, IEEE, 53.2, 90-97 (2015).
15. Hecklau, F., Galeitzke, M., Flachs, S., Kohl, H. Holistic approach for human resource
management in industry 4.0. Procedia CIRP, 54, 1-6 (2016).
16. Dorofeyuk, A. A. Expert-classification analysis methodology in control and complex data
processing problems (history and future prospects). Control Sci., 3.1., 19–28 (2009).
17. Chen, Z., Pappas, N., Kountouris, M. Probabilistic caching in wireless D2D networks:
cache hit optimal versus throughput optimal. IEEE Commun Lett, 21(3), 584–587 (2017).
18. Shah, A., Ghahramani, Z. Parallel predictive entropy search for batch global optimization
of expensive objective functions. Advances in Neural Information Processing Systems,
3330–3338 (2015).
19. Neittaanmäki, P., Repin, S., Tuovinen, T. (Eds.). Mathematical Modeling and
Optimization of Complex Structures; Series: Computational Methods in Applied Sciences.
Springer International Publishing AG, Switzerland (2016).
20. Azar, A., Miao, G. Network lifetime maximization for cellular-based M2M networks.
IEEE Access, 5,18927–18940 (2017).
21. Tsyrkov, A.V., Tsyrkov, G.A. Intelligent components to support workflow in the design
and production activities. Proceedings of the 2017 International Conference “Quality Man-
agement, Transport and Information Security, Information Technologies” (IT&QM&IS),
IEEE, 764–768 (2017).