=Paper=
{{Paper
|id=Vol-2258/paper54
|storemode=property
|title=Intelligent Time Series Forecasting System
|pdfUrl=https://ceur-ws.org/Vol-2258/paper54.pdf
|volume=Vol-2258
|authors=Vadim Borisov,Pavel Komarov,Victor Luferov
}}
==Intelligent Time Series Forecasting System==
https://ceur-ws.org/Vol-2258/paper54.pdf
Intelligent time series forecasting system
V V Borisov1, P I Komarov2 and V S Luferov1
1
The Branch of National Research University «Moscow Power Engineering Institute» in
Smolensk, Smolensk, Russia
2
The branch of Financial University of the Russian Federation
Abstract. The developed intellectual system for forecasting time series based on artificial
neural networks, adaptive neural-fuzzy models and models based on the decomposition of
fuzzy time series is considered. The developed system is designed for modeling time series by
various methods in order to select the best model in terms of accuracy for operation in
forecasting tasks. The system provides ample opportunities and convenient interface for
acquiring knowledge, skills in creating, teaching, comparing the results of applying intelligent
models and methods for solving theoretical and practical problems of analyzing and forecasting
time series in different subject areas.
1. Introduction
Currently, there is a large number of time-series (TS) forecasting systems [1-2], which, as a rule, are
oriented toward the implementation of two classes of methods for forecasting TS: statistical and
intellectual. In contrast to statistical methods, intelligent methods for predicting TS are characterized
by the ability to take into account mutually influencing (in not only correlating) different-quality
factors.
At the same time, for these models there is a problem of determining their type, structure. In
addition, IT professionals, rather than domain specialists, who often do not have the required skills in
the field of information systems design, carry out the creation of intelligent forecasting systems (IFS).
This leads to a more complicated process and a justified increase in the development time of the IFS.
Currently, the most popular language tools for creating intelligent systems are R, Python
programming languages using the capabilities of mathematical packages such as MatLab [3].
However, to forecast time series based on intelligent models, domain specialists need to know the
relevant software tools.
2. Structure of intelligent time series forecasting system
Based on the above, it is possible to determine the following main characteristics, which must have
intelligent time series forecasting system (ITSFS):
an intuitive interface that allows domain specialists to create, configure, modify and use
intelligent models quickly and easily to forecasting time-series;
ease of specifying interdependencies between input and output parameters, taking into account
the required «depth» of autoregression;
455
automatic generation and verification of training samples for intelligent models of various
types;
flexible change in the structure and parameters of intellectual models in the process of
forecasting TS.
An intelligent time series forecasting system is proposed, the structure of which is shown in Figure
1.
The module for analysis and
The module for learning sample
accounting of the influence of time
generation
series
Module for choosing the type of Module for time series generation
intellectual model
Module for building and teaching The database
User interface
intelligent models module
User
Module for forecasting time series
База
База
The моделей
моделей
base of
intellectual
A comparison module for the models
results of forecasting time series
The module for the formation of the resulting calculations
Figure 1. Structural diagram of the proposed ITSFS.
The database module accumulates data from external sources. External data sources can be
enterprise database management systems, data tables, specialized data files, expert opinions, etc. The
time series generation module converts unstructured data into time series with varying degrees of
discretization. Time series can be changed at any stage of the work of the intellectual time series
forecasting system If necessary, a time series can be specified by entering data through the user
interface.
The module for analyzing and accounting for time series interactions allows the user to perform
time series analysis, determine correlation, autocorrelation, etc. The analysis of time series allows
specialists to substantiate the correctness of the construction of models, to find out trends and patterns
that are subsequently accumulated and used to account for the relationship between input and output
variables. When analyzing time series, the user interacts with the module through an intuitive
interface.
When the module for forecasting time series predicts, the following steps are performed:
1. construction of linguistic variables based on the clustering algorithm;
2. formation of fuzzy rule base based on clustering algorithm;
3. training model based on retrospective data obtained from the fuzzy partitioning module, and
the output of training results
4. forecasting electric load potential forecast horizon.
456
After the implementation of forecast verification data occurs, if there is reference data, and output
the results.
From the set of time series using the module of training sample formation for time series, the
relationships between output and input variables are formed and selected with allowance for
autoregression:
P(t 1) f P(t ), P(t 1), U (t 1), U (t ),... ,
where P(t 1) – forecasted value of time series; P(t ) – the previous value of the forecasted time series;
U (t 1), U (t ) – time series that have a direct or indirect effect on the forecasted time series.
3. Libraries of intelligent time series forecasting system
The subject domain expert selects and configures the models presented in the model database that
contains three types of intelligent models from the following libraries:
FANN (Fast Artificial Neural Network);
FL (FuzzyLogic);
FTSD (Fuzzy Time Series Decomposition).
FANN (Fast Artificial Neural Network) is a library for constructing and using artificial neural
networks for forecasting time series. This library provides an interface for tuning and subsequent use
of artificial neural networks (ANN) such as multilayer perceptron. The library is available on the
Internet at: http://leenissen.dk/fann/wp/.
This library has the following features:
ANN training on back propagation of the error;
transformation of the ANN structure in the learning process;
comes with open source;
library is cross-platform.
FL (FuzzyLogic) is a library for using fuzzy inference models based on the Mamdani and Sugeno
algorithms for forecasting time series. The library was developed by one of the authors of this article
and is available on the Internet at: https://github.com/Luferov/FuzzyLogic. Based on the Sugeno fuzzy
inference algorithm, an adaptive network-based fuzzy inference system output is implemented. The
model is trained by back propagation of the error [4-5].
The library has the following features:
use of Mamdani and Sugeno fuzzy inference algorithms;
implementation of the «mountain» clustering algorithm for model training;
implementation of the algorithm for fuzzy expansion of time series for flexible separation of
time series into trend and residual components, depending on the specified «step» of the fuzzy
partition [6].
FTSD (Fuzzy Time Series Decomposition) is a library for building forecastion models based on
fuzzy time series decomposition. The peculiarity of forecasting time series based on time series
decomposition consists in isolating the trend component from the time series at each prediction step
and in tracking the dynamics of the process in forecasting.
The module for building and teaching intelligent models initializes the intellectual model chosen by
the expert (it`s type and structure). Based on the established relationship, the model is trained, its
adequacy is estimated and the reliability of the time series forecasting.
After training, time series forecasting is performed using the module for forecasting time series. In
the process of forecasting, the expert can perform structural and parametric adjustment of the model.
The results of the forecast, obtained with the use of different intellectual models, can be compared
with each other and with reference values by means of the comparison module for the results of
forecasting time series. Depending on the results of the comparison, the decision is made to choose the
best or correct the models used, using the module for generating the resulting calculations.
To demonstrate the efficiency of the developed intelligent time series forecasting system, consider
the operational and short-term time series forecasts.
457
As an operational forecast (for 24 hours), let's consider use of ITSFS developed on the example of
comparison of the results of the electrical load of the Smolensk region in December 2017 with the use
of intelligent models of various types: artificial neural network (from the FANN library), neuro-fuzzy
model (from the FL library), models based on fuzzy time series decomposition (from the FTSD
library). The graphs of the electric load forecasts obtained using these models are shown in figure 2.
The operational projections are presented in table 1 and the comparative evaluation is presented in
table 2.
Figure 2. Graphs of operational forecasts based on intellectual models of various types.
Table 1. The result of the operational forecast using various smart models.
Predictive Predictive
Predictive
Reference value value
value using
hour
value, using a using a
a FL,
MWt FANN, FTSD,
MWt
MWt MWt
1 30341 28267,54 25209,71 29354,52
2 29491 28034,06 25678,35 28447,74
3 29091 27964,68 26246,61 28571,51
4 28896 28073,92 26914,06 29191,89
5 29062 28279,21 27560,84 29490,97
6 29848 28741,88 28422,04 30050,22
7 31091 29385,47 29406,78 30707,12
8 33022 30462,73 31295,97 31900,28
9 34341 31412,77 32614,22 33225,01
458
10 35537 32178,21 33519,3 34323,55
11 35636 32716,33 33763,95 34335,99
12 35496 33109,36 33867,82 34017,17
13 35225 33342,39 33793,18 33992,74
14 35122 33575,44 34109,01 34192,62
15 35165 33556,03 34530,65 34280,33
16 35425 33365,72 34562,23 34209,4
17 35960 33171,02 34828,68 34005,97
18 36546 32909,38 35047,84 33843,16
19 36449 32612,72 35338,31 33675,62
20 36032 32161,64 34801,14 33419,44
21 35430 31681,77 33882,99 33099,67
22 34772 31244,32 32525,8 32749,12
23 33477 30908,3 30951,73 31976,78
24 31899 30658,4 29766,65 31027,17
Table 2. Comparison of the operational forecasting results.
Intellectual model MAPE, %
Predictive value using a FANN 6.76
Predictive value using a FL 5.73
Predictive value using a FTSD 4.76
Table 3. Comparison of the short-term forecasting results.
Intellectual model MAPE, %
Predictive value using a FANN 4.20
Predictive value using a FL 3.85
Predictive value using a FTSD 4.13
As a short-term forecast (for 31 days), let's consider the use of the developed ISP BP by comparing
the results of the electrical load of the Smolensk region in December 2017 with the use of intelligent
models of various types: artificial neural network (from the Fann library), neuro-fuzzy model (from
the FL library), models based on fuzzy time series decomposition (from the ftsd library). The graphs
of the electric load forecasts obtained using these models are shown in figure 3. The results of the
comparative evaluation are presented in table 3.
459
The forecasting of time series is carried out on the basis of intellectual models according to the
general algorithm. First, the final resultant sample is constructed, depending on the relationship
established between the input and output time series by the expert. Then the data is normalized, i.e. all
values of the initial data of the training sample are reduced to a single hypercube. This is important for
comparing time series to bring them to a single scale. If normalization is not necessary, the training
sample is applied to the model in a «raw» form. Then the validation of the intellectual model is carried
out, the horizon of possible forecasting is specified and the time series in the training sample is
compared. After that, the intellectual model is trained on a trained training sample. As a result, a
forecasted series is formed, which can be presented either in the form of a report, or used when
compared with the results of forecasting by other models.
Building a training sample based on a specified relationship
[time series normalization is used]
[No]
[Yes]
The application of the normalization The use of training samples in the
factor to the training sample forecast model
Entering a normalized training sample
into the forecast model
Validation of the forecast model
[Validation errors occurred]
[Validation passed successfully]
The output of the error message
Training of intellectual forecast model
Output of forecasting results and report
generation
Figure 3. UML diagram of time series forecasting on the basis of mental models.
The developed ITSFS can be recommended as a teaching system for students in the field of
«Informatics and Computer Science», and will also be useful for students of other areas and specialists
engaged in the analysis and modeling of complex systems and processes under uncertainty, the
creation of intelligent information systems and technology.
4. Conclusion
460
The paper presents the developed intellectual time-series forecasting system that provides ample
opportunities and convenient interface for acquiring knowledge, skills and skills in creating, teaching,
comparing the results of applying intelligent models and methods for solving theoretical and practical
problems of time series analysis and forecasting in various subject areas. The developed system is
designed for modeling time series by various methods in order to select the best model in terms of
accuracy for operation in forecasting tasks.
5. References
[1] Averkin A N, Kosterev V V Triangular norms in systems of artificial intelligence // Izvestiya
Akademii Nauk. Theory and control systems, 2000. №5. – PP. 106–109. (in Russian)
[2] Halliwell J, Keppens J, Shen Q Linguistic Bayesian networks for reasoning with subjective
probabilities in forensic statistics// Proc. of the 5th International Conference on AI and Law,
2003. – PP. 42–50
[3] Leonenkov A V Fuzzy modeling in MATLAB and fuzzyTECH. – St.-Petersburg: BHV–
Petersburg, 2003. –736 p. (in Russian).
[4] Borisov V V, Kruglov V V, Fedulov A S Fuzzy models and networks. 2-nd ed. stereotype. –
Moscow: Hot line-Telecom, 2012. –284 p. (in Russian)
[5] Borisov V V, Fedulov A S, Zernov M M Basics of hybridization of fuzzy models. Series
“Fundamentals of fuzzy mathematics”. Book 9. Textbook for high schools. – Moscow: Hot
Line–Telecom, 2017. –100 p.
[6] Afanasyeva T V, Namestnikov A M, Perfilieva I G, Romanov A A and Yarushkina N G
Forecasting time series: fuzzy models; under the scientific. Ed. N.G. Yarushkina. – Ulyanovsk:
UlSTU Publishing House, 2014. – 145 p.
Acknowledgment
The work was supported by the Russian Science Foundation, project No. 16-19-10568.
461