A comprehensive review on hybrid network traffic prediction model

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 11, No. 2, April 2021, pp. 1450~1459
ISSN: 2088-8708, DOI: 10.11591/ijece.v11i2.pp1450-1459  1450
Journal homepage: http://ijece.iaescore.com
A comprehensive review on hybrid network traffic prediction
model
Jinmei Shi1
, Yu-Beng Leau2
, Kun Li3
, Joe Henry Obit4
1,2,4
Faculty of Computing and Informatics, Universiti Malaysia Sabah, Kota Kinabalu, Malaysia
1
Hainan Vocational University of Science and Technology, Haikou Hainan, China
3
College of Engineering, Bohai University, Jinzhou, China
Article Info ABSTRACT
Article history:
Received Apr 22, 2020
Revised Sep 10, 2020
Accepted Oct 11, 2020
Network traffic is a typical nonlinear time series. As such, traditional linear
and nonlinear models are inadequate to describe the multi-scale characteristics of
traffic, thus compromising the prediction accuracy. Therefore, the research to
date has tended to focus on hybrid models rather than the traditional linear
and non-linear ones. Generally, a hybrid model adopts two or more methods
as combined modelling to analyze and then predict the network traffic.
Against this backdrop, this paper will review past research conducted on
hybrid network traffic prediction models. The review concludes with a
summary of the strengths and limitations of existing hybrid network
prediction models which use optimization and decomposition techniques,
respectively. These two techniques have been identified as major
contributing factors in constructing a more accurate and fast response hybrid
network traffic prediction.
Keywords:
Decomposition technique
Hybrid model
Mode decomposition
Particular swarm optimization
Quantum genetic
Traffic prediction
Wavelet transform
This is an open access article under the CC BY-SA license.
Corresponding Author:
Yu-Beng Leau
Faculty of Computing and Informatics
Universiti Malaysia Sabah
Jalan UMS, 88400, Kota Kinabalu, Sabah, Malaysia
Email: lybeng@ums.edu.my
1. INTRODUCTION
With the huge tide of the internet driving the rapid development of society, computer network has
since become an important technical means of the information society. In order to guarantee the quality of
network services such as video conferencing, online gaming and the like, the increment of network traffics is
necessary [1, 2]. Due to the large volume of traffic flow in and flow out in the network, data is being leaked
or disclosed every day [3-5]. It is hard to detect the abnormalities as well as propose preventive remedies to
minimize the security risks in advance [6, 7]. Consequently, network failures caused by potential malicious
intrusions and virus invasions have triggered serious concerns among the network management and
monitoring team [8-10].
Network traffic is an important parameter to evaluate the running state of a network. It is found to
be a nonlinear time series [11] which has the characteristics of time-variability, long-term correlation, self-
similarity, suddenness and chaos [12]. Therefore, a more accurate and fast response traffic prediction model
is much desired to ensure a safe and healthy network situation. According to Joshi [13], network traffic prediction
is a reliable method to secure the network communication in a network management and monitoring system. It is
a process which analyses the characteristics of traffic in the past and present, generates the rules of internal
structure and then constructs a model to predict the characteristics and trends of future traffic.

Int J Elec & Comp Eng ISSN: 2088-8708 
A comprehensive review on hybrid network traffic prediction model (Jinmei Shi)
1451
A hybrid model was first proposed by Bates and Granger who integrated the merits of the individual
models [14]. However, Dickinson confirmed that the variance error of the hybrid predicting model is less
than any of the single models [15]. In Yang et al. similarly contended that the prediction error of a hybrid
model is lower than a single nonlinear model. Given that, it is feasible to use hybrid models to predict the
network traffic [16]. Since the earlier works, a considerable amount of literature has been published on
hybrid network prediction models. These studies generally applied the optimization and decomposition
techniques in the hybrid model to produce a better prediction accuracy.
In this paper, the recent hybrid models are comprehensively reviewed. The paper is structured as
follows. Section 2 reviews the application of optimization technique in the hybrid model while the utilization
of decomposition techniques in the hybrid model will be investigated in the following section. The final part
of the paper concludes with a summary.
2. OPTIMIZATION TECHNIQUES-BASED HYBRID MODEL
In order to better describe the traffic characteristics and improve the accuracy of the prediction
model, researchers have recently combined various methods into a single prediction model and optimize it
with different optimization techniques such as particular swarm optimization (PSO) [17], and quantum genetic
(QG) [18, 19] among others.
2.1. PSO-based hybrid model
The random determination of the input weights and hidden biases [20] of extreme learning machine
(ELM) can lead to ill-condition problem, resulting in low prediction. In Fei Han selected PSO algorithm with
simple principle, and proposed the APSO-ELM hybrid model to address the drawbacks of ELM. He adopted
adaptive algorithm to optimize PSO which selects the input weights and hidden biases. Then he used moore-
penrose (MP) generalized inverse to analytically determine the output weights of ELM. In order to obtain
optimal parameters of ELM, the improved PSO optimizes the input weights and hidden biases. In this case,
the model not only obtains the optimal root mean square error (RMSE), but it also obtains the optimal output
weight norm. This directly solves the problems caused by "randomness" of ELM and consequently improves
the accuracy of the prediction model. It should be noted that his paper will only focus on the parameter
problem of ELM which will affect the accuracy of the model but will ignore the drawbacks of local optimal
solution of PSO [21].
The PSO algorithm with simple principle and few parameters can shorten the training speed of
neural network, which in turn improves the convergence speed of the model. Based on this idea, in Yi Yang,
combined the three algorithm models and proposed a new hybrid method which she called SPLSSVM. She
also used PSO to optimize the two parameters of least squares support vector machine (LSSVM). Then,
based on the seasonal adjustment (SA) and LSSVM, she reduced the seasonal interference on the traffic
components to predict network traffic [17]. But the hybrid model only considers the seasonal characteristics
of traffic and also ignores the problem of local optimal solution of PSO.
Based on the same design idea, Weijie Zhang similarly utilised PSO algorithm with simple principle
to optimize structural parameters of RBF neural network. By adjusting the inertia weight and learning factor
to improve the global search ability in the global extremum search, he was able to solve and avoid local
optimal solution of PSO. Then he optimized the four parameters of the RBF so as to obtain the accuracy of
the prediction model [22]. Lamentably, in the process of obtaining global optimal solutions, RBF has too
many parameters to be optimized, and this will increase the calculation scale, the training time and affect the
convergence rate.
In the view that PSO algorithm has a simple principle but local optimal solution problem, He et al.
in 2016, introduced Quantum non-gate to realize mutation operation. He used particle flight path information
to dynamically update the status of quantum bit so as to avoid local optimization drawbacks of PSO. Then, he
used IPSO to optimize the weight, width and center position parameters of radial basis function (RBF)
network. He was able to realize optimized parameters neural network and establish self-adaptive PSO-RBF
hybrid model. As such, the network traffic data with nonlinear characteristics can be predicted and the
difficulty of prediction is reduced significantly [23]. Inevitably, he solved the problem of PSO, yet neglected
the complex calculation principle of Quantum algorithm. Considering the difficulty of approaching the global
optimal solution, the prediction accuracy is consequently affected.
As discussed above, these authors have used different methods to solve the local optimal solution
problem of PSO. However, they have all ignored the salient fact that there are too many parameters of RBF
optimization and the training time is too long to approximate the optimal solution. In effect, the optimal
solution of PSO was not effectively solved, thus affecting the convergence speed and accuracy.

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 11, No. 2, April 2021 : 1450 - 1459
1452
2.2. QG-based hybrid model
Considering that the limitation of traditional network traffic time series prediction model and the
problem that back propagation (BP) neural network is easy to get into local solution. The limitations of
traditional network traffic time series prediction model and the BP neural network have been widely
acknowledged in the literature. In this light, in Kun Zhang introduced the Quantum algorithm with strong
global optimization ability and the PSO algorithm with simple principle. He applied the combination
algorithm to solve the gradient explosion problem of BP, and he then proposed the QPSO-BP hybrid model.
To elaborate, when QPSO algorithm is applied to the training stage of prediction model, a set of weights that
minimize the error function in competitive time can be obtained. The weight is updated gradually until the
convergence criterion is satisfied. After that, the objective function to achieve the minimization is the
prediction error function so as to improve the prediction accuracy of the model [24]. Inevitably, in the
process of iterative training, the computation scale of Quantum algorithm is very heavy [25]. So, it is still
difficult to approach the global optimization and obtain the local optimal solution.
In view of the shortage of BP neural network, the prediction error and jitter of the model are easily
large. Hui Tian also used algorithm to optimize the structure of BP network based on efficient global search
capability of quantum genetic algorithm (QGA). Then, he applied wavelet technology (WT) to decompose
the traffic into low frequency and high frequency data. He subsequently proposed WT-QGA-BP hybrid
model to predict the chaos of network traffic. However, the model ignored two important facts the wavelet
technology has signal noise with the signal, and the Quantum mechanical calculation scale is too large. These
issues will increase the complexity of the hybrid model, resulting in low generalization performance [26].
As the algorithm developed and evolved, researchers found that although the fruit fly optimization
algorithm (FOA) can easily fall into the problem of local optimization solution, it still has the strengths of
simple calculation and coding convenience. In Ying Han used Quantum mechanics theory to optimize FOA.
Then he used QFOA to optimize five important parameters of echo state network (ESN) and proposed
QFOA-ESN hybrid model to provide model accuracy. The model is best described as follows: first, the
phase-space reconstruction technology is used to reconstruct the original network traffic data series;
afterwards, the ESN method is used to build the prediction model. Meanwhile the model parameters are
optimized by the QFOA. Finally, the optimal ESN model is used for multi-step prediction for the network
traffic [27]. However, the model has too many optimization parameters and the computation scale of
Quantum can become larger. Hence, in the process of training, these will affect the convergence rate and
accuracy of the hybrid model. Both authors (i.e., names) evidently solved the limitations of neural network.
Yet, they all ignored the fact that although the Quantum algorithm can solve the global optimization, the
training time of the model due to the large amount of computation and complex calculation scale is increased.
This makes it difficult to solve the optimal solution which will in turn affect the accuracy and convergence
rate of the prediction model.
2.3. Other hybrid model
RBF neural network has the advantage of global approximation to nonlinear function. Hence, it can
predict the network traffic data with nonlinear characteristics. Based on this, in Dengfeng Wei introduced the
gravity search algorithm (GSA) to optimize the RBF network structure and improve the convergence rate of
the prediction model. On one hand, the method can optimize the parameters such as the center ci of the basic
functions of hidden units, width ri and network connection weights wkj of RBF. On the other, the fitting
result and nonlinear approximation ability of RBF neural network are better used to obtain the optimal neural
network prediction model. In the iteration process, RBF parameters are lamentably too many to be optimized
so as to obtain local optimal solution problem [11].
Aiming at the gradient explosion of BP neural network and the local optimal solution of long short-
term memory (LSTM). In view of the gradient explosion of BP neural network and the local optimal solution
of long short-term memory (LSTM), Azzouni, in 2017, proposed a LSTM-RNN (recurrent neural network,
RNN) hybrid framework to predict traffic matrix. By validating the framework on real-world data from
GEANT network, he used the sliding learning window method to solve the LSTM neural network
limitations. Then he combined it with RNN neural network to extract the dynamic characteristics of network
traffic and predict the future traffic. Although his work managed to solve the LSTM’s limitation using the
sliding learning window method, the total number of time slots became too large, resulting in high
computational complexity [28].
In the same year, based on the same problem of LSTM neural network, Qinzheng Zhuo proposed a
model of neural network which can be used to combine LSTM with deep neural networks (DNN). The aim
was to solve the network traffic prediction of autocorrelation nonlinear time series data. Auto-correlation
coefficient is then added to the model to improve the accuracy of the prediction model. This model boasts
higher precision when compared to the other traditional models. After considering the autocorrelation

1453
features, the neural network of LSTM and DNN has clear advantages in the accuracy of the large granularity
data sets. However, the e model is only applicable to the network with autocorrelation traffic characteristics [29].
With the rapid development of technology and given the same drawbacks of LSTM which can result
in some deviation of the prediction results, Duan in 2018, focused on filtering noise flow data to mitigate the
deficiencies of LSTM. Based on the idea of decomposition, he proposed the seasonal loess trend
decomposition (ST) and LSTM prediction model. The model process method is aimed at dealing with
periodic traffic data, decomposing trend and eliminating random noise. But the hybrid model is limited in use
in that it can only address the periodic characteristics of traffic, and not the nonlinear multi-scale
characteristics of traffic data [30].
As is evident, different researchers focus on different optimization algorithms. To address the
problem of "prematurity" of FOA algorithm, Han optimized the ESN neural network based on the
Opposition-Based Learning mechanism. He also solved FOA's defect in order to realize multi-step prediction
of network traffic. He first used the phase space reconstruction technique to reconstruct the original network
flow time series and establish the model based on the ESN method. Then, using opposition-based learning
mechanism of fruit flies optimization algorithm, he optimized the model parameters. Finally, the optimized
model is used to realize the multi-step prediction of network traffic. However, there are four parameters of
ESN which must be optimized, making it too large to approximate the optimal solution, thus affecting the
accuracy [31].
In Wenquan Xu, posited that the existing traffic model should focus on finding parameters such as
the weight of node connection in the neural network. If the appropriate value cannot be obtained, the model
parameter search remains in the local optimal, hence resulting in a compromised model precision. Due to
this, the author used auto-regressive (AR) model to fit the original data and obtain the AR model residuals
between the original data and the predicted data of the AR model. The residuals are regarded as the nonlinear
component and are taken as inputs into the deep belief network (DBN) model. The AR model prediction and
the output of the DBN model are the final forecasting value for the time series. Inevitably, in the process of
substantial trainings and residuals, the model has to be constantly adjusted by the coefficient, thus leading to
an increase in the calculation scale and time [32]. For a better understanding of the application of the optimization
technique in the hybrid model in terms of its strengths and limitations, a comparison is presented in Table 1 in the
Appendix.
In a nutshell, researchers have used different optimization algorithms to construct traffic models
which have higher performance. While they have sufficiently considered the drawbacks of single neural
network, some limitations remain [33, 34]. To build better accurate models, researchers are constantly trying
out new techniques and methods. With the development of research, the idea based on decomposition is
gradually introduced into the prediction field of traffic timing.
3. DECOMPOSITION TECHNIQUE-BASED HYBRID MODEL
In the new era of hybrid model construction, researchers introduce time-frequency analysis into
traffic law analysis and apply the signal analysis theory to traffic time series analysis. Therefore,
decomposition techniques are now widely used in hybrid models, mainly wavelet transform (WT) [35] and
mode decomposition (MD) such as empirical mode decomposition (EMD) [36], ensemble empirical mode
decomposition (EEMD) [37] and variational mode decomposition (VMD) [38]. These time series traffic
hybrid models are fast becoming a hot topic for researchers.
3.1. WT-based hybrid model
The network traffic has the characteristics of remote dependence and multifractal, rendering the
single neural network model an inadequate prediction tool. In Laisen Nie, introduced decomposition idea and
used discrete wavelet transform (DWT) to divide the signal into low-pass and high-pass components.
gaussian model (GM) predicted high-pass components and deep belief network (DBN) model predicted low-
pass components, estimating the parameters of the Gaussian model by the maximum likelihood method. Then
he predicted the high-pass component by DWT-DBN-GM hybrid model [39]. Based on the same notion,
Laisen Nie also adopted the DWT method to decompose the signal. The author used spatiotemporal
compressive sensing (SCS) method to predict high-pass components and DBN model to predict low-pass
components. He subsequently proposed the DWT-DBN-SCS hybrid model [40]. Using this model, the defect
of single neural network is solved, but the difficulty of decomposition scale of wavelet transform (WT) [41]
is overlooked, which can then affect the accuracy of the hybrid model.
Considering the difficulty of accurately predicting complex network traffic data in the LSTM model,
Haipeng Lu et al. introduced wavelet transform (WT) to construct WT-LSTM hybrid model in 2018. Firstly,
the traffic is decomposed to an approximation sequence and several detail sequences. The approximation

 ISSN: 2088-8708
1454
sequence contains the trend and cyclical features of traffic, whereas the detail sequences contain the detailed
information at multiscale. Then the approximation sequence is used to train the LSTM network, while the
detail sequences are used to construct the empirical detail sequences. By reconstructing sequence with
predicted approximation sequence and empirical detail sequences, the prediction of future traffic is acquired.
However, the limitations of WT are similarly ignored and the problem of local optimal solution of LSTM
remains unsolved [42].
Given that the decomposition scale of WT technique is difficult, Madan et al. used inverse discrete
wavelet transform (iDWT) technology to decompose the traffic into details and approximate components.
Through the iDWT reconstruction, the sequence is reconstructed to obtain a new time series. Then the
selected ARIMA model is used to predict the low component, and the RNN neural network is used to predict
the high component, respectively. The proposed hybrid model is a time series which can be used to predict
the future traffic trends in a computer network. The model has sufficiently solved the harder problem of
WT’s decomposition scale. However, the complexity of calculation in RNN is ignored, hence the accuracy of
prediction model can be questionable [43].
3.2. MD-based hybrid model
The constraints of WT technology and single neural network include the tendencies of falling into
local minimum, and over fitting. The selection of network structure is also too dependent on experience.
These limitations directly affect the reliability of neural networks for time series prediction and modelling. In
Tian Zhongda first proposed to decompose traffic into stable data signals of different characteristic scales
based on Empirical mode decomposition (EMD) technology. The components after decomposing remove the
long correlation and the different yet prominent local characteristics of time series which can in turn reduce
the non-stationary of time series. He then proposed the EMD-ELM hybrid model with the incorporation of
the ELM neural network [44]. Unfortunately, EMD is prone to mode aliasing and endpoint effect problems [45]
during the decomposition process which can eventually compromise the prediction accuracy.
In view of the traffic long and short correlation, Chen introduced the EMD-PSO-SVM hybrid model
based on empirical mode decomposition, particle swarm optimization and support vector machine. First, the
EMD s used to eliminate the influence of traffic noise signals. Then particle swarm optimization algorithm is
used to optimize the parameters of SVM. The effectiveness of the presented method is examined by
evaluating it with different methods including basic SVM and EMD. Finally, SVM is used for model training
and fitting traffic model [46]. While this model can improve the accuracy of network traffic prediction, it
ignores the model aliasing problem and endpoint effects of EMD; the definiteness of model prediction is
subsequently affected.
To address the limitation of EMD, Wanwei Huang introduced ensemble empirical mode
decomposition (EEMD) technology and quantum neural network algorithm to construct the QNN-EEMD
hybrid model. The EEMD technique is used to decompose the time series into IMF to remove modal aliasing
and redundancy. Then he used QNN to process the decomposed IMF and optimize the parameters of the
model so that the convergence speed of the hybrid model is improved [47]. However, the model ignores the
impact of too large computation scale of Quantum algorithm mechanics. In addition, the EEMD dependence
on amplitude and number of experiences [48] will affect the accuracy of the prediction.
Due to the deficiencies of EMD and EEMD, Lina Pan argued that ESN can easily suffer from the
influences of initial random weights. She first introduced the concept of variational mode decomposition
(VMD) to overcome the problems of EMD and EEMD and effectively decompose the traffic. Using Bat
Algorithm (BA) algorithm to improve and optimize ESN parameters, she then proposed the VMD-BA-ESN
network traffic hybrid prediction model. In the process of the decomposition, VMD is utilized to decompose
the original internet traffic series into several band-limited intrinsic mode functions (BLIMFs). Inevitably,
decomposition layers will be an important factor to determine the accuracy of prediction [49].
Given the strong non-stationary and high complexity of the chaotic time series, it is difficult to
directly analyse and predict by just depending on a single model. Hence, in Xinghan Xu applied a two-layer
decomposition approach and optimized BP neural network. The hybrid model aims to obtain comprehensive
information of the chaotic time series which is composed of complete ensemble empirical mode decomposition
with adaptive noise (CEEMDAN) and variational mode decomposition. The VMD algorithm is used for
further decomposition of the high frequency subsequence obtained by CEEMDAN, after which the prediction
performance is significantly improved. Then the BPNN optimized by a firefly algorithm (FA) is utilized for
prediction. The hybrid model fully considers the importance of decomposition signals. However, it ignores
the performance of VMD determined by the number of decomposition layers, which is likely to cause over-
decomposition or under-decomposition and can affect the accuracy of the model [50].
In view of the extensive application of decomposition technique in network traffic prediction and
attempts to improve the prediction accuracy of nonlinear non-stationary traffic data, Ying Han, et al.,

1455
proposed a IFOA-ESN combined prediction model. This model is based on VMD by Levy flight function
and cloud generator. First, VMD is used to decompose the original network traffic data into several subsets.
Then, multiple sub reservoirs are built after performing the phase space reconstruction (PSR) of each data
subset. Finally, the training set is used to train the prediction model. This mechanism solves the problem of
VMD requiring a certain number of pre-set patterns and iteration factors, which cannot be determined by
subjective experience. Unfortunately, the synchronous optimization inside and outside of the multiple sub
reservoirs necessitates longer calculation time. This can negatively affect the training time of the model and
the convergence speed as well as the performance of the model mechanism. Thus, the bigger calculation
scale remains an unsolved scientific conundrum [51]. The strengths and limitations of the decomposition
technique in the hybrid network traffic prediction model are summarized in Table 2 in the Appendix.
4. CONCLUSION
In conclusion, optimization and decomposition are two important processes in a hybrid network
traffic prediction model in ensuring a higher prediction accuracy and faster convergence speed. This paper
found that PSO as well as other optimization algorithm can generally identify network traffic time sequences
better given its strengths of simple principle, small calculation scale, fast convergence speed and so forth.
The paper also confirmed that the decomposition technique is an effective method to deal with non-linearity
and non-stationarity of data as it provides a modelling idea based on the time frequency analysis for traffic
analysis. Especially, VMD can overcome the multiresolution and decomposition scale problem in WT, solve
the problem of mode aliasing and white noise amplitude in EMD and EEMD decomposition techniques. The
review has, to some extent, helped enhance our understanding of the importance of optimization and
decomposition techniques in a hybrid network prediction model. The parameter optimization of decomposition
technique and optimization algorithm is the key process to determine the prediction accuracy and convergence rate.
Future research should therefore concentrate on the investigation of how to simplify the optimization algorithm
with fewer parameters, shorten the convergence speed and improve the decomposition effects to subsequently
enhance the network traffic prediction accuracy.
APPENDIX
Table 1. Application of optimization technique in hybrid model
No. Year Author Original Model Hybrid Model Strength Limitation
1 2013 Fei Han, et
al., [21]
Particle swarm
optimization
APSO-ELM Optimizes input weight and
deviation of ELM based on the
adaptive PSO algorithm.
The problem of local optimal
solution of PSO is still not
solved and may affect the
accuracy of the model.
Extreme learning
machine
2 2013 Kun Zhang,
et al., [24]
Particle swarm
optimization
QPSO-BP Solves BP gradient explosion
based on the Quantum
algorithm and PSO.
The quantum algorithm is
difficult to calculate; l easy to
fall into the local optimal
solution.
Quantum
BP neural network
3 2014 Yi Yang, et
al., [17]
Seasonal transform SA-PSO-LSSVM Sequence elimination by SA
reduces the interference of
seasons on components and
optimizes two parameters of
LSSVM based on the PSO.
Only considers the seasonal
characteristics of traffic but
ignores the PSO local optimal
solution.
Particle swarm
optimization
Least squares support
vector machine
4 2016 Deng Feng
Wei [11]
Gravity search algorithm IGSA-RBF Improves the speed selection
formula based on the GSA and
optimizes three parameters of
RBF.
GSA lacks theoretical
guidance; RBF optimization
parameters are too many; easy
to fall into the local optimal
solution problem.
Radial basis function
neural network
Particle swarm
optimization
5 2016 Tao He, et
al., [23]
Radial basis function
neural network
PSO-RBF Avoids local optimization
drawback of PSO with Quantum
bit and optimizes the weight,
width and center position of
RBF network based on the
IPSO.
PSO iteratively optimizes the
three parameter processes of
RBF, which makes it difficult
to approach the global
optimal.
Particle swarm
optimization
Black hole
6 2017 Abdelhadi
Azzouni, et
al., [28]
Recurrent neural network RNN-LSTM Solves LSTM problem by
sliding learning window and
extracts the dynamic
characteristics of traffic based
on the RNN.
While solving the LSTM
problem, the accuracy of
prediction is improved, but
the complexity of calculation
is neglected.
Long short-term memory

 ISSN: 2088-8708
1456
Table 1. Application of optimization technique in hybrid model (continue)
7 2017 Qinzheng
Zhuo, et al..
[29]
Deep learning neural
network
LSTM-DNN Solves LSTM problem and fully
considers the autocorrelation and
timing characteristics of traffic.
It is applicable to networks
with autocorrelation
characteristics.
Long short-term memory
8 2017 Ying Han, et
al., [27]
Echo State Network QFOA-ESN Solves the local optimization
solution of FOA based on the
quantum mechanics and
optimizes five important
parameters of ESN with QFOA.
Has too many optimization
parameters and too much
computation, which affects the
convergence rate.
Fruit optimization
algorithm
Quantun
9 2017 Ying Han
[31]
Echo state network OBL-FOA-ESN Optimizes FOA based on the
OBL and then optimizes four
parameters of ESN model to
provide model accuracy.
The optimization parameters
are too many; the calculation
is large, the structure is
complex will in turn affect the
convergence speed.
Fruit fly optimization
Algorithm
10 2018 Weijie
Zhang, et al.,
[22]
Radial basis function IPSO-RBF Optimizes PSO by using
mutation method to avoid local
minimum problem and then
optimizes three parameters of
RBF.
It is difficult to approach the
global optimal solution due to
too many parameters when
using IPSO to optimize RBF.
Particle swarm
optimization
Adjusting inertia weight
and learning factor
11 2018 Hui Tian, et
al., [26]
Quantum genetic
algorithm
WT-QGA-BP Determines embedded dimension
and associated dimension based
on the C-C and G-P algorithm;
reconstructs and optimizes BP
based on the WT.
WT can easily cause signal
noise interference, and
decomposition scale is
difficult; new model is too
complex and lowers the
generalization performance.
Wavelet transform
BP neural network
12 2018 Qi Duan, et
al., [30]
Long short-term memory SLT-LSTM The non-stationary, correlated
and periodic traffic data are
processed by SLT to decompose
the trend and eliminate the
random noise.
Only pays attention to the data
characteristics of network
traffic, while ignoring
nonlinear multi-scale
characteristics of traffic.
Seasonal loess trend
13 2018 Wenquan Xu
et al., [32]
Deep learning neural
network
DBN-AR/ARIMA Computes residuals traffic data
based on the AR and ARIMA;
adjusts the model coefficients
after training the residuals.
Constantly adjusts by the
residuals and coefficient, and
the calculation scale and time
will continue to increase.
Deep belief network
AR/ARIMA model
Table 2. Application of decomposition technique in hybrid model
1 2017 Laisen Nie,
et al., [39]
Discrete wavelet
transform
DWT-DBN-GM It is divided into low and high-pass
components by DWT; Gaussian
model predicts high-pass
component, while DBN method
predicts low-pass component.
Ignores the difficulty of wavelet
decomposition scale and the
complexity of the new model
structure, leading to low
Gaussion model
Deep belief network
2 2017 Lina Pan,
et al., [49]
Echo state network VMD-BA-ESN Decomposes the complex sequence
into several simple components by
VMD; global optimization is used
to determine the initial weight of
ESN and reduces the influence.
Decomposition layers affect the
decomposition effect and
ultimately affect the accuracy
of prediction.
Variational mode
decomposition
Bat algorithm
3 2018 Laisen Nie,
et al., [40]
Discrete wavelet
transform
DWT-DBN-SCS It is divided into low and high-pass
components by DWT; DBN model
predicts low-pass component,
whereas SCS method predicts
high-pass component.
Ignores the difficulty of wavelet
decomposition scale and the
complexity of the new model
structure, leading to low
Deep belief network
Spatiotemporal
compressive sensing
4 2018 Haipeng
Lu, et al.,
[42]
Long short-term memory WT-LSTM Decomposes the traffic by WT and
predicts based on the WT-LSTM
hybrid model.
The scale difficulty of WT and
the local optimal solution of
LSTM are not well dealt with.
Wavelet transform
5 2018 Rishabh
Madan, et
al., [43]
Discrete wavelet
transform
DWT-ARIMA
-RNN
Decomposes reconstruction traffic
into details and approximates
components by iDWT; ARIMA
model is used to predict the low
component and RNN is used to
predict the high component.
The signal decomposition and
reconstruction issues are
sufficiently addressed, but the
calculation of RNN is difficult
and the WT decomposition
scale is complex.
AR/ARIMA model
Recurrent neural network
6 2018 Tian
Zhongda
[44]
Empirical mode
decomposition
EMD-ELM Decomposes the traffic into stable
data signals with different
characteristic scales by EMD;
combines the advantages of ELM's
fast learning speed to improve the
accuracy of network traffic
prediction.
The ELM random input weights
deviations and mode aliasing of
EMD can inversely impact the
accuracy of the model.
Extreme learning
machine
Seasonal loess
trend decomposition
process method

1457
Table 2. Application of decomposition technique in hybrid model (continue)
7 2018 Wanwei
Huang, et al.,
[47]
Ensemble empirical
mode decomposition
QNN-EEMD Decomposition time series into
IMF by EEMD so as to remove
modal aliasing and optimize
parameters of QNN model to
avoid local optimal solution.
Focuses on solving the problem
of signal decomposition, but how
to optimize the EEMD dependent
amplitude and experience is still
a challenge
Artificial neural network
Quantun
8 2019 Wenbo
Chen, et al.
[46]
Empirical mode
decomposition
EMD-PSO-
SVM
Eliminates noise from data based
on the EMD, and optimizes SVM
based on the PSO.
The influence of modal aliasing
in EMD on model accuracy is
ignored.
Support vector machine
Particle swarm
optimization
9 2019 Xinghan Xu,
et al., [50]
BP neural network CEEMD-
VMD-FA-
BPNN
Improves EEMD defects by
increasing adaptive white noise
amplitude and forms a two-stage
decomposition with VMD
technology; optimizes the
threshold and weight of BP
neural node based on FA to
improve the ability of function
approximation to neural network.
Ignores the number of VMD
decomposition layers which can
influence the decomposition
effect, thus reducing the
prediction accuracy of the model.
Variational mode
decomposition
Ensemble empirical
mode decomposition
Firefly algorithm
10 2019 Ying Han, et
al., [51]
Variational mode
decomposition
VMD-PSR-
IFOA-ESN
Improves FOA with the cloud
model and the levy flight function
to optimize VMD modes and
iterative factor;the sub-modes
after VMD decomposition are
reconstructed by PSR;ESN
multiple subreservoirs is
automatically built according to
optimized decomposition results
by VMD.
The new combined model needs
longer calculation time, which is
due to synchronous optimization
inside and outside of the multiple
sub reservoirs. This will impact
the training time of the model
and affect the convergence speed
and the performance of the model
prediction.
Phase space
reconstruction
Cloud generator
Fruit fly optimization
algorithm
Echo state network
ACKNOWLEDGEMENTS
The authors would like to thank Faculty of Computing and Informatics, University Malaysia Sabah
and also Hainan Vocational University of Science and Technology under 2019 Academic Cooperation and
Collaborative Education Project of China Ministry of Education (No. 201901012008).
REFERENCES
[1] Jittawiriyanukoon C., “Approximation of regression-based fault minimization for network traffic,” TELKOMNIKA
Telecommunication, Computing, Electronics and Control, vol. 18, no. 4, pp. 1802-1808, 2020.
[2] Chakravarthy V. D. and Amutha B., “Path based load balancing for data center networks using SDN,” International
Journal of Electrical and Computer Engineering (IJECE), vol. 9, no. 4, pp. 3279-3285, 2019.
[3] Khin Swe Yin and May Aye Khine, “Optimal remote access trojans detection based on network behavior,”
International Journal of Electrical and Computer Engineering (IJECE), vol. 9, no. 3, pp. 2177-2184, 2019
[4] Algelal Z. M., Ghanialdhaher E. A., Abdul-Wadood D. N., “Botnet detection using ensemble classifiers of network
flow,” International Journal of Electrical and Computer Engineering (IJECE), vol. 10, no. 3, pp. 2543-2550, 2020.
[5] Boukhalfa A., Abdellaoui A., Hmina N., et al., “LSTM deep learning method for network intrusion detection
system,” International Journal of Electrical and Computer Engineering (IJECE), vol. 10, no. 3, pp. 3315-3322, 2020.
[6] Lysenko S., Bobrovnikova K., Matiukh S., et al., “Detection of the botnets' low-rate DDoS attacks based on self-
similarity,” International Journal of Electrical and Computer Engineering (IJECE), vol. 10, no. 4, pp. 3651-3659, 2020.
[7] Shetty N. P., Shetty J., Narula R., et al., “Comparison study of machine learning classifiers to detect anomalies,”
International Journal of Electrical and Computer Engineering (IJECE), vol. 10, no. 5, pp. 5445-5452, 2020.
[8] Kong, W., Dong, Z. Y., Jia, Y., Hill, D. J., Xu, Y., Zhang, Y., “Short-Term Residential Load Forecasting Based on
LSTM Recurrent Neural Network,” IEEE Transactions on Smart Grid, vol. 10, no. 1, pp. 841-851, 2019.
[9] Chen, K., Yan, Z. J., and Huo, Q., “A context-sensitive-chunk BPTT approach to training deep LSTM//BLSTM
recurrent neural networks for offline handwriting recognition,” 2015 13th International Conference on Document
Analysis and Recognition (ICDAR), Tunis, 2015, pp. 411-415.
[10] Wheeb A H., “Performance evaluation of UDP, DCCP, SCTP and TFRC for different traffic flow in wired
networks,” International Journal of Electrical and Computer Engineering (IJECE), vol. 7, no. 6, pp. 3552-3557, 2017.
[11] Wei, D., “Network trafﬁc prediction based on RBF neural network optimized by improved gravitation search
algorithm,” Neural Computing and Applications, vol. 28, no. 8, pp. 2303-2312, 2017.
[12] Li, Q., and Lin, R.-C., “A New Approach for Chaotic Time Series Prediction Using Recurrent Neural Network,”
Mathematical Problems in Engineering, vol. 2016, 2016, pp. 1-9.
[13] Joshi, M. R., and Hadi, T. H., “A Review of Network Traffic Analysis and Prediction Techniques,”
arXiv:1507.05722, 2015.

 ISSN: 2088-8708
1458
[14] Bates J. M. and Granger C. W., “The combination of forecasts,” Operational Research Quarterly, vol. 20, no. 4,
pp. 451-468, 1969.
[15] Dickinson J. P., “Some comments on the combination of forecasts,” Operational Research quarterly, vol. 26, no. 1,
pp. 205-210, 1975.
[16] Yang, Y., Chen, Y., Li, C., Gui, X., Li, L., “Network Traffic Prediction Based on LSSVM Optimized by PSO,”
2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic
and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its
Associated Workshops, Bali, 2014, pp. 829-834.
[17] Eberhart, R., and Kennedy, J., “A New Optimizer Using Particle Swarm Theory,” MHS'95. Proceedings of the
Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, 1995, pp. 39-43.
[18] Holland J. H., “Genetic algorithms and the optimal allocation of trials,” SIAM Journal on Computing, vol. 2, no. 2,
pp. 88-105, 1973.
[19] Narayanan, A., and Moore, M., “Quantum-inspired genetic algorithms,” Proceedings of IEEE International
Conference on Evolutionary Computation, Nagoya, Japan, 1996, pp. 61-66.
[20] Lan, Y., Soh, Y. C., and Huang, G. Bin, “Two-stage extreme learning machine for regression,” Neurocomputing,
vol. 73, no. 16-18, pp. 3028-3038, 2010.
[21] Han, F., Yao, H., and Ling, Q., “An improved evolutionary extreme learning machine based on particle swarm
optimization,” Neurocomputing, vol. 116, pp. 87-93, 2013.
[22] Zhang, W., and Wei, D., “Prediction for network traffic of radial basis function neural network model based on
improved particle swarm optimization algorithm,” Neural Computing and Applications, vol. 29, no. 4, pp. 1143-1152, 2018.
[23] He, T., Dan, T., Wei, Y., Li, H., Chen, X., Qin, G., “Particle swarm optimization RBF neural network model for
internet traffic prediction,” 2016 International Conference on Intelligent Transportation, Big Data & Smart City
(ICITBS), Changsha, 2016, pp. 521-524.
[24] Zhang, K., Liang, L., and Huang, Y., “A Network Traffic Prediction Model Based on Quantum Inspired PSO and
Neural Network,” 2013 Sixth International Symposium on Computational Intelligence and Design, Hangzhou,
2013, pp. 219-222.
[25] Nayak, S., Nayak, S., and Singh, P. J. P., “An Introduction to Quantum Neural Computing,” Journal of Global
Research in Computer Science, vol. 2, no. 8, pp. 50-55, 2011.
[26] Tian, H., Zhou, X., and Liu, J., “A hybrid network traffic prediction model based on optimized neural network.
Parallel and Distributed Computing,” 2017 18th International Conference on Parallel and Distributed Computing,
Applications and Technologies (PDCAT), Taipei, 2017, pp. 284-287.
[27] Han, Y., Jing, Y., and Li, K., “Multi-step prediction for the network traffic based on echo state network optimized
by quantum-behaved fruit fly optimization algorithm,” 2017 29th Chinese Control and Decision Conference
(CCDC), Chongqing, 2017, pp. 2270-2274.
[28] Azzouni A., Pujolle G., “A long short-term memory recurrent neural network framework for network traffic matrix
prediction,” arXiv preprint arXiv:1705.05690, 2017.
[29] Zhuo, Q., Li, Q., Yan, H., Qi, Y., “Long short-term memory neural network for network traffic prediction,” 2017
12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), Nanjing, 2018, pp. 1-6.
[30] Duan, Q., Wei, X., Gao, Y., Zhou, F., “Base Station Traffic Prediction based on STL-LSTM Networks,” 2018 24th
Asia-Pacific Conference on Communications (APCC), Ningbo, China, 2018, pp. 407-412.
[31] Han, Y., and Li, K., “Improved FOA-ESN method using opposition-based learning mechanism for the network
traffic prediction with multiple steps,” 2017 Chinese Automation Congress (CAC), Jinan, 2017, pp. 7183-7187.
[32] Xu, W., Peng, H., Zeng, X., Zhou, F., Tian, X., Peng, X., “A hybrid modelling method for time series forecasting
based on a linear regression model and deep learning,” Applied Intelligence, vol. 49, pp. 3002-3015, 2019.
[33] Gao X., Sun L., Sun D., “An enhanced particle swarm optimization algorithm,” Information Technology Journal,
vol. 8, no. 8, pp. 1263-1268, 2009.
[34] Elroby M. M. H., Mekhamer S. F., Talaat H. E. A., et al., “Population based optimization algorithms improvement
using the predictive particles,” International Journal of Electrical and Computer Engineering (IJECE), vol. 10, no. 3,
pp. 3261-3274, 2020.
[35] Riedi, R. H., Ribeiro, V. J., and Baraniuk, R. G., “A Multifractal Wavelet Model with Application to Network
Traffic," IEEE Transactions on Information Theory, vol. 45, no. 3, pp. 992-1018, 1999.
[36] Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Yen, N., Liu, H. H., “The empirical mode
decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,” Royal Society of
London Proceedings Series A, vol. 454, no. 1, pp. 903-995, 1998.
[37] Zhang, J., Yan, R., Gao, R. X., Feng, Z., “Performance enhancement of ensemble empirical mode decomposition,”
Mechanical Systems and Signal Processing, vol. 24, no. 7, pp. 2104-2123, 2010.
[38] Dragomiretskiy, K. and Zosso, D., “Variational mode decomposition,” IEEE Transactions on Signal Processing,
vol. 62, no. 3, pp. 531-544, 2014.
[39] Nie, L., Jiang, D., Yu, S., Song, H., “Network Traffic Prediction Based on Deep Belief Network in Wireless Mesh
Backbone Networks,” 2017 IEEE Wireless Communications and Networking Conference (WCNC), San Francisco,
CA, 2017, pp. 1-5.
[40] Nie, L., Wang, X., Wan, L., Song, H., Jiang, D., “Network Traffic Prediction Based on Deep Belief Network and
Spatiotemporal Compressive Sensing in Wireless Mesh Backbone Networks,” Wireless Communications and
Mobile Computing, vol. 2018, 2018.

1459
[41] Peng, Z. K., Tse, P. W., and Chu, F. L., “An improved Hilbert-Huang transform and its application in vibration
signal analysis,” Journal of Sound and Vibration, vol. 286, no. 1-2, pp. 187-205, 2005.
[42] Lu, H., and Yang, F., “A Network Traffic Prediction Model Based on Wavelet Transformation and LSTM
Network,” 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS),
Beijing, China, 2018, pp. 1-4.
[43] Madan, R., and Sarathi, M. P., “Predicting Computer Network Traffic: A Time Series Forecasting Approach using
DWT, ARIMA and RNN,” 2018 Eleventh International Conference on Contemporary Computing (IC3), Noida,
2008, pp. 1-5.
[44] Tian, Z., Mao, C., Wang, G., and Ren, Y., “Approach for time series prediction based on empirical mode
decomposition and extreme learning machine,” 2018 Chinese Control and Decision Conference (CCDC),
Shenyang, 2018, pp. 3119-3123.
[45] Deering, R., and Kaiser, J. F., “The use of a masking signal to improve Empirical Mode Decomposition,”
Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005,
Philadelphia, PA, vol. 4, pp. iv/485-iv/488, 2005.
[46] Chen, W., Shang, Z., and Chen, Y., “A Novel Hybrid Network Traffic Prediction Approach Based on Support
Vector Machines,” Journal of Computer Networks and Communications, vol. 2019, 2019.
[47] Huang, W., Zhang, J., Liang, S., and Sun, H., “Backbone Network Traffic Prediction Based on Modiﬁed EEMD
and Quantum Neural Network,” Wireless Personal Communcations, vol. 99, pp. 1569-1588, 2018.
[48] Du, S., Liu, T., Huang, D., Li, G., “An Optimal Ensemble Empirical Mode Decomposition Method for Vibration
Signal Decomposition,” Journal of Vibration and Acoustics, vol. 39, no. 3, pp. 031003(1)-021003(18), 2016.
[49] Pan, L., Cheng, J., Li, H., Zhang, Y., Chen, X., “An Improved Echo State Network Based on Variational Mode
Decomposition and Bat Optimization for Internet Traffic Forecasting,” 2017 IEEE 17th International Conference
on Communication Technology (ICCT), Chengdu, 2017, pp. 417-421.
[50] Xu, X., and Ren, W., “SS symmetry A Hybrid Model Based on a Two-Layer Decomposition Approach and an
Optimized Neural Network for Chaotic Time Series Prediction,” Journal Symmetry, vol. 11, no. 5, p. 610, 2019
[51] Han, Jing, Li., and Dimirovski, G. M., “Network Traffic Prediction Using Variational Mode Decomposition and
Multi-reservoirs Echo State Network,” IEEE Access, vol. 7, pp. 138364-138377, 2019.
BIOGRAPHIES OF AUTHORS
Jinmei Shi PhD Student, Computer Science, Faculty of Computing and Informatics, University
Malaysia Sabah. She has been engaged in research and teaching for 11 years and has always been
in the forefront of scientific research. She plays an active role in the construction of computer
science and personnel training, and has good practical experience and academic foundation. She
mainly researches network traffic prediction, algorithm analysis and software. In recent years, she
has been published 10 papers, 3 sponsored projects, 3 book, and 10 awards above the provincial
level.
Yu-Beng Leau is a senior lecturer of Computer Science at the Faculty of Computing and
Informatics, Universiti Malaysia Sabah in Malaysia. He received his B.Sc degree (Multimedia
Technology) from Universiti Malaysia Sabah, M.SC degree (Information Security) from Universiti
Teknologi Malaysia and PhD degree (Internet Infrastructures Security) from Universiti Sains
Malaysia. His current research interests are intrusion alert detection and prediction, network
security situation awareness, IPv6 security, Internet of Things (IoT) and Information Centric
Network (ICN).
Kun Li was received the B.Sc. degree from Shandong University of Science and Technology in
2005,and received his M.Sc. degree from Liaoning Technical University in2008,and received His
Ph.D. degrees from Northeastern University Shenyang of China in 2013. He is currently an
Associate Professor in College of Engineering, Bohai University. His current research works focus
on complex industrial process modeling, intelligent optimal control, machine learning, and their
application.
Joe Henry Obit is an Associate Professor of Computer Science, department of Data Science at
Universiti Malaysia Sabah. His main research interest lies at the interface of Operational Research
and Computer Science. In particular, the exploration and development of innovative Operational
Research, Artificial Intelligence, and Distributed Artificial Intelligence models and methodologies
for automatically producing high quality solutions to a wide range of real world combinatorial
optimization and scheduling problems. Dr. Joe Obtained his PhD in Computer Science from the
School of Computer Science at the University of Nottingham. His PhD thesis is developing a
Novel Meta-heuristic, Hyper-heuristic and Cooperative Search.

A comprehensive review on hybrid network traffic prediction model

More Related Content

What's hot (20)

Similar to A comprehensive review on hybrid network traffic prediction model (20)

More from IJECEIAES (20)

Recently uploaded (20)

A comprehensive review on hybrid network traffic prediction model