Skip to main content

Über dieses Buch

This book constitutes the refereed proceedings of the 14th International Conference on Systems Simulation, Asia Simulation 2014, held in Kitakyushu, Japan, in October 2014. The 32 revised full papers presented were carefully reviewed and selected from 69 submissions. The papers are organized in topical sections on modeling and simulation technology; network simulation; high performance computing and cloud simulation; numerical simulation and visualization; simulation of instrumentation and control application; simulation technology in diversified higher education; general purpose simulation.



Modeling and Simulation Technology

Modeling and Simulating the Walking Behavior of Small Pedestrian Groups

In the virtual environment, the current methods can simulate some virtual human behaviors realistically. However, these methods take the crowd as a collection of separate individuals, which is difficult to generate interactive behaviors of the virtual crowd, especially for the small pedestrian groups with fewer members. Based on establishing the basic set of formations, this paper will model the walking behavior of small pedestrian groups, and control the interaction between group members. Regarding to the group with more members, we firstly separate the group into multiple smaller groups, and design an algorithm to maintain the consistency and adhesion between these detached groups. The simulation results show that the small pedestrian groups generated by our method can adjust their formations automatically according to the changing environment, and accomplish collision-free movement. Visually speaking, the behaviors of the small group we model are authentic.

Yue-Wen Fu, Meng Li, Jia-Hong Liang, Xiao-Qian Hu

Application of PID Neural Network Decoupling Control in Deaerator Pressure and Deaerator Water Level Control System

The deaerator pressure and deaerator water level are intercoupling in marine steam power plant. Traditional PID control strategy is difficult to get satisfactory control effect. We must take corresponding decoupling measures. This paper proposes a deaerator pressure and deaerator water level decoupling control strategy based on PID neural network, with which we can make comprehensive utilization of the advantage of both PID and neural network. Results of the simulation show that compared with traditional PID control strategy, the PID neural network decoupling control strategy can provide more stability and faster response speed in deaerator pressure and deaerator water level control.

Peng Wang, Hao Meng, Qing-zhou Ji

Estimation of an Impulse Response Using Kurtosis

In this paper, we propose a method of estimating an impulse response of a system by using kurtosis. The kurtosis is used for a measurement of the non-Gaussianity and the sharpness of probability distribution. The probability distribution of the sum of i.i.d. random variables is close to the Gaussian distribution in comparison with the original distribution. This theorem is called the central limit theorem. Based on the central limit theorem, we estimate the impulse response by maximizing the kurtosis of an estimated noise that is obtained from an observed signal and an input signal to the system.

Keito Kito, Takahiro Murakami

Modeling and Solution for Virtual Channel Scheduling for Downlink Business

Virtual Channel (VC) facility in AOS protocol divides one physical channel into multiple independent virtual channel. Virtual channel scheduling (VCS) is an important approach to transfer large capacity of data efficiently. In this work a comprehensive model for VCS is established, and the model considers general optimal of quality of service (QoS) requirements for different data, including delay, jitter, throughput and loss packet rate. A genetic algorithm (GA) based method is designed to solve the model, and a group of experiments are conduced to test the established model and proposed method.

Yating Zhu, Peng Wan, Yu Chen, Fei Tao, Lin Zhang

Analysis of Server Distribution Policies in Peer-Assisted File Distribution with Flash Crowds

With the growing popularity of peer-assisted file distribution in commercial applications, flash crowds have a significant impact on download performance. A file distribution system has to cope with extreme flash crowd conditions that correspond with a sudden surge in peer arrivals. In such systems, service providers have to ensure that the system has sufficient capacity to maintain the agreed quality of service at minimum costs. Using our measurement-driven analytic model, we investigate four different server distribution policies for peer-assisted file distributions with heterogeneous peers bandwidth. Our policies are designed to reduce the server data usage without increasing expected peer download time. We observed that increasing the server bandwidth allocated for slow peers and decreasing that for fast peers can be effective in reducing the average download time by 5% and server provisioning data usage by 10%, without affecting the fairness of the system. Secondly, when server bandwidth is reduced by 70% during maximum utilization and increased during the end-game phase, the total server data decreases by 12% with 4.3% improvement in peer download performance.

Cristina Carbunaru, Yong Meng Teo

Design of Fault Diagnosis Set Membership Filter for Systems with Nonlinear State Constraints

In this paper, the design of set membership filter is considered for discrete-time systems with nonlinear equality constraint. The nonlinear equality constraint is first linearized with linearizing truncation error and base point error which are uncertain quantities. Assuming that ellipsoids are applied to bound the process noise, measurement noise, fault signal, and linearing errors. Then all inequalities are combined by using S-procedure method. Finsler’s Lemma is employed to project the unconstrained set membership filter onto the constrained surface. LMI is developed for designing the set-membership filter with nonlinear equality constraint. Finally, a recursive algorithm is proposed to compute the state and fault ellipsoid that guarantee to contain the true value. The method of fault diagnosis based on the set membership filter with nonlinear state constraints not only can estimate the size of the fault, but also can detect the type of fault signal. The simulation result shows that the method presented is available and effective.

Ye-Long Mu, Lin-Lu Miao

Controller Design Approach Based on Multi-variable Sliding Mode Control

This paper explains and demonstrates the controller design approach based on the multi-variable sliding mode control (SMC). Many conventional SMCs are constructed as a servo system. Herein, we design a reference model in the SMC servo system, so that the plant output follows the reference model output. The switching function, including the model state variables, is determined, before calculating a linear plant input, in order to keep the state trajectory on the switching surface. A nonlinear plant input is determined in order to allow the state variable to reach and remain on the switching surface, so that the matching condition is satisfied. The plant state variables are estimated by an observer, and the optimal feedback gain and the integral gain are determined by the linear quadratic regulator (LQR). We confirmed the effectiveness of the proposed method by performing simulations for several plants.

Ryo Tanaka, Takehito Fujio, Hiromitsu Ogawa, Takahiro Murakami, Yoshihisa Ishida

A Color Mapping Method for Decimated Model

In this paper we present a method for coloring the surface of the decimated mesh with an original texture without reparametrization. This approach combines the generation of the dense triangle mesh on each mesh element with the vertex color interpolation across the planes of the new generated triangles. The proposed method minimizes the texture distortion that is obtained by the displacement of points on the mesh during the decimation processing. The suggested approach provides transformation of an original model with texture at-tributes to the model with the decreased size and color-mapped surface.

Bo Yu, Maria Savchenko, Luis Diago, Junichi Shinoda, Ichiro Hagiwara

Network Simulation

A Novel Hybrid Web Service Discovery Algorithm

As web services on the Internet expands quickly, how to search web services automatically, accurately and fast has become a difficult issue in service-oriented computing. Responding to the problems existing in an open and dynamic environment in the service discovery studies such as low search efficiency, unbalanced loading and semantic inefficiency, this paper puts forward a hybrid service discovery algorithm based on referral network and ant colony algorithm. Firstly, this paper constructs a self-organizing service referral network model and provides policy for the algorithm. Secondly, this paper raises a service discovery algorithm based on ant colony and basis of self-organizing service referral network model. The experimental results show that the algorithm can improve success rate and recall ratio of web service discovery.

Peng Zhu, Fei Jia

Rectangular Slot Antenna with Asymmetrical Conductor Strip for Bandwidth Enhancement Coverage UWB Standard

This paper presents the bandwidth enhancement of rectangular slot antenna fed by microstrip line on the flexible Mylar Polyester film substrate. Asymmetrical conductor strip is designed and inserted in the rectangular slot to extend the bandwidth from 3.06 GHz to 7.2 GHz frequency range. Besides, the rectangular conductor at the end of the feeding microstrip line is introduced for increasing the bandwidth at high frequency up to 12.32 GHz. This improved antenna to cover standard frequency range of UWB (3.1 GHz -10.6 GHz). Finally, as to reject the frequency band of IEEE 802.11a (5.15 GHz – 5.35 GHz), the line strip at the side of tuning stub is added. In this case, the band-notched frequency from 5.15GHz to 5.38 GHz can be easily obtained.

Tuanjai Archevapanich, Paitoon Rakluea, Noppin Anantrasirichai, Boonchana Purahong, Vanvisa Chutchavong

Ultra-Wideband Slot Antenna on Flexible Substrate for WLAN/WiMAX/UWB Applications

An ultra-wideband slot antenna on flexible substrate is designed to support a wide range of wireless communication systems. The antenna is a rectangular slot antenna fed by microstrip line with conductor strip and tuning stub on flexible substrate (Mylar Polyester film). The rectangular slot is etched out from the ground plane with conductor strip in the slot, and the other plane contains a microstrip line with tuning stub. The proposed antenna’s effective frequency range covers overall standard bands of WLAN, WiMAX, and UWB. The antenna was simulated and analyzed by using IE3D Zeland software [1]. And the simulation results presents the characteristics of the antenna in terms of bandwidth return loss, VSWR, and radiation patterns.

Tuanjai Archevapanich, Mayuree Lertwatechakul, Paitoon Rakluea, Noppin Anantrasirichai, Vanvisa Chutchavong

High Performance Computing and Cloud Simulation

Performance Tuning of Vlasov Code for Space Plasma on the K Computer

Space plasma is a collisionless, multi-scale, and highly nonlinear medium. Thus computer simulations are essential for full understanding of space plasma. In the present study, we develop a high-performance parallel Vlasov (collisionless Boltzmann) simulation code which is the first-principle method for collisionless space plasma. The performance tuning of the code has been made on various supercomputer systems such as the K computer, FX10 and CX400 supercomputer systems. The performance efficiency of more than 15% is achieved on these systems.

Takayuki Umeda, Keiichiro Fukazawa

An Approach to Optimized Resource Allocation for Cloud Simulation Platform

Resource allocation for simulation applications in cloud simulation environment brings new challenges to infrastructure service providers. In order to meet the constraint of SLA and to allocate the available virtualized resources optimally, this paper first presents autonomic resource management architecture, and then proposes a resource allocation algorithm for infrastructure service providers who want to minimize infrastructure cost and SLA violations. Our proposed algorithm can maximize the overall profit of infrastructure service providers when SLA guarantees are satisfied or violated in a dynamic resource sharing cloud simulation platform. The experimental evaluation with a realistic workload in cloud simulation platform, and the comparison with the existing algorithm demonstrate the feasibility of the algorithm and allow a cost-effective usage of resources in cloud simulation platform.

Haitao Yuan, Jing Bi, Bo Hu Li, Xudong Chai

An Enhanced User-Based Collaborative Filtering Recommendation System Using the Users’ Latent Relationships Weighting Utilization

Nowadays, A Recommendation system is an important technique in the development of electronic-commerce services and the most concerned approaches used in a recommendation system is a collaborative filtering algorithm, which uses the preference of users to make predictions. However, it works poorly to handle the sparse data. There are several previous methods used to deal with the weakness of collaborative filtering techniques such as the row-sampling approximating singular value decomposition algorithm, but the results show their disadvantages in practical use. In this paper, we propose an enhanced user-based collaborative filtering algorithm using users’ latent relationships weighting (CF-ULRW), which we have used in the predicted rating process. In the experiments, our proposed method is compared with the user-based collaborative filtering and the row-sampling approximating singular value decomposition. The experimental results show that our proposed method outperforms other methods with the same dataset.

Thi Thuan To, Sutheera Puntheeranurak

A Port&Event-Graph-Based Method for PDES Objects Development

As the complexity of simulation objects increases, the manual programming method for developing them is of low efficiency and high requirements. The traditional event graph provides a graphical developing method, but there exists tight coupling and poor reusability with the built simulation objects. According to the problems, this paper proposes a port&event-graph-based method for PDES objects development, which introduces ports into the event graph to decouple the scheduling relationship, to improve the independence of simulation objects. The experimentation shows this method can help improve the development efficiency and the constructed simulation objects have good reusability and are easy to be used.

Feng Yao, Yiping Yao, Wenjie Tang, Feng Zhu, Yuan Liu

Numerical Simulation and Visualization

Progress of Binary-Collision-Approximation-Based Simulation for Surface Erosion by Plasma Irradiation

The investigation of the erosion process of plasma facing material under plasma irradiation is an important issue for the achievement of the steady-state operation of nuclear fusion devices. Although binary-collision-approximation-based (BCA) simulation is a powerful tool for the investigation of plasma-material interaction, there is a difficulty to apply the simulation to the investigation of dynamical process of erosion because BCA simulation neglects two physical processes, i.e., diffusion process of retained plasma particles in material and structural relaxation process of material. In this paper, therefore, we develop an extended BCA simulation taking account of diffusion and relaxation processes for the calculation of erosion of materials under plasma irradiation.

Seiki Saito, Masayuki Tokitani, Hiroaki Nakamura

Multiple Scatter Plots Based Multi-dimensional Transfer Function for Visualizing Ocean Simulation Data

This study proposes a multiple scatter plots based multi-dimensional transfer function for visualizing characteristic structures from ocean simulation data. In the proposed method, characteristic features are manually extracted in a couple of 2-dimensional scatter plots using visual effect and empirical judgment based on user’s existing knowledge. Extracted structures in each 2-variable space are assigned to other color dimensions such as Hue, Saturation and Brightness for the purposes of feature specification and classification. We applied the proposed method to high-resolution ocean data in two different regions. Ocean currents are intuitively extracted in multiple scatter plots and represented using multi-dimensional transfer functions.

Daisuke Matsuoka, Fumiaki Araki, Yumi Yamashita

1-D Shallow Water Models for Dam Break Flash Floods with Different Junction and Bend Treatments

Recently-developed Finite Element/Volume Methods for the cross-sectionally averaged 1-D shallow water equations in open channel networks are applied to idealized and real cases of dam break flash floods for their examination on robustness and versatility. The major differences among the schemes are the treatments of junctions and bends in the momentum equation as the internal boundary conditions. The computational results show robustness of the schemes. The results also show critical influences of the internal boundary conditions on the water surface profiles and flood arrival times, indicating that a necessary ingredient for their successful prediction is evaluation of the momentum flux with appropriately considering the channel configurations.

Hidekazu Yoshioka, Koichi Unami, Masayuki Fujihara

A Point Cloud Registration Method Based on Point Cloud Region and Application Samples

In this study, a new automatic point cloud registration algorithm based on point cloud registration is proposed to broaden registration ways. The proposed method extracts features of point cloud region for performing the coarse registration. Based on the coarse registration results, the Iterative Closest Point (ICP) algorithm is used for performing the fine registration to restore the measured model. The proposed registration approach is able to do automatic registration without any assumptions about initial positions, and avoid the problems of traditional ICP algorithm in the bad initial estimation. The proposed method along with ICP algorithm provides efficient 3D modeling for computer-aided engineering, computer-aided design and application with Kinect.

Yujing Liao, Fang Xu, Xilu Zhao, Ichiro Hagiwara

Fused Visualization for Large-Scale Time-Varying Volume Data with Adaptive Particle-Based Rendering

Recently, there is a strong need for the fused visualization of different objects in many simulation fields, especially for the medical domain (e.g., the fusion of different organs). That is because it is desirable and advantageous to show the different objects and analyze the relationship between them. Nevertheless, such a simulation date is always resulted in a large-scale time-varying volume data, which make the fused visualization even more difficult. To solve this problem, we use a sorting-free rendering technique, Adaptive Particle-based Rendering (APBR), to visualize the large-scale time-varying volume data. Because this method visualizes the volume data by generating opaque particles from the original volume data and projects these particles to the image plane, the visibility sorting is not needed. This makes the fusion of different objects and handling of large-scale volume data is very easy. Moreover, our proposed APBR method can adaptively apply different particle generation process to visualize the volume data based on different viewpoints. This feature can make our system keep an interactive frame rate and also a relatively high image quality. With the APBR, we also develop a time-varying rendering into our system so that the rendering for the large-scale time-varying data also becomes possible. To verify the efficiency, we apply our APBR system to the large-scale blood flow dataset. The experimental results and the user feedbacks show that our system can fuse different objects efficiently while keeping an interactive frame rate and a good image quality, which is very meaningful in the visual analysis.

Kun Zhao, Naohisa Sakamoto, Koji Koyamada

3D Fluid Scene Synthesizing Based on Video

We present an approach for synthesizing larger 3D fluid scene with frame example of video. Both rich realistic texture and height field of fluid particles are employed to study. Realistic textures can enhance the synthesized fluid appearance, whereas the height field enable the generation of complex geometry and stochastic movement on the surface. Our method achieves a good trade off between the visual quality and the production cost. It includes four steps of height field calculating, belt areas clustering according to main components of height field histogram, 3D fluid scene constituting, and transition smoothing both in geometry and appearance. To generate temporally coherent 3D fluid scene over a fluid sequence, we transport fluid video information of colors, height values and particle texture coordinates over fluid sequence. We demonstrate our synthesis results for different scales of larger fluid scenes in several challenging scenarios and provide qualitative evaluation to our method.

Hongyan Quan, Hanyu Xue, Xiao Song

Simulation of Instrumentation and Control Application

Application of Intensified Current Search to Optimum PID Controller Design in AVR System

The intensified current search (ICS) is one of the newest metaheuristic optimization search techniques for solving the continuous optimization problems. It is the latest modified version of the original current search (CS). In this paper, the algorithms of the ICS is proposed and the performance evaluation of the ICS is investigated via five well-known surface optimization problems. The ICS is then applied to design an optimum PID controller for the AVR widely used in power systems. Based on the optimization context, the sum of absolute errors between reference input and output response of the system is performed as the objective function to be minimized. This paper demonstrates how to conduct the ICS to search efficiently the optimum PID controller parameters of the AVR system. As results, the optimum PID controller for the AVR system is successfully and rapidly obtained by the ICS. Moreover, the ICS-based design approach performs high robustness once parameter variations are occurred in the control loop.

Auttarat Nawikavatan, Satean Tunyasrirut, Deacha Puangdownreong

DSP-Based Speed Control of Brushless DC Motor

This paper presents design and implements the speed control of BLDC motor drive based on TMS320F28335 DSP controller board in order to be used for MATLAB/SIMULINK. The PI controller design by pole placement technique is also introduced to the system for regulating and tracking speed response. This scheme leads to the speed adjustment of the BLDC motor by PWM. This experiment aims to examine the effectiveness of BLDC motor by testing 100 watt to BLDC motor system from no load to rated condition. It is found that, the speed of BLDC motor can be controlled to be constant in the operating range of 700 rpm and 1400 rpm at no load and full load.

Danupon Kumpanya, Satean Tunyasrirut

Exploting the Orthonormal Function Based on Model Predictive Control for Automotive Application

In this paper, we introduced and explored the Laguerre and Kautz functions as an orthonormal functions based of model predictive control approach for automotive applications with particularly focuses on vehicle path following control and motor position control. The first implementation starting with the known trajectory, model predictive control based on linearized vehicle and tire model was used to follow the desired trajectory as close as possible, we performed a vehicle at middle speed maneuver on double lane change scenario. In the second application; predictive control is designed in order to track the desired motor position. We compared the predictive controllers designed based on Delta, Laguerre and Kautz functions for both applications in term of tracking error and position error performances. The result showed that the predictive control based on Kautz function gave a better tracking performance compared to Laguerre function and Delta function (conventional method). However, Laguerre function is easier and simpler in term of algorithm implementation than the other two functions. Moreover, for all functions based on predictive control; the simulation results demonstrated that orthonormal function can be implemented in predictive control approaches particularly to automotive application, thus, it is believe can be extended to other applications.

Fitri Yakub, Yasuchika Mori

Simulation Technology in Diversified Higher Education

Feedback Preferences in Case-Base Construction for Intelligent Lab Tutor

Development of e-learning tools has been researched widely since 1900’s. Virtual laboratory (VL) has been one of the tools implemented, and it has given a great impact on student’s learning. However, the learning process become more challenging, as the students perform the experiments without any guidance from a human tutor. Consequently, this paper proposes the development of a case-based Intelligent Lab Tutor (ILT) to assist the learning process. The ILT is expected to provide scaffolding to students during their experiment sessions using the virtual lab. We intend to adopt student preferences as the initial case-base for the ILT. A questionnaire is distributed to a group of engineering students, and analyzed to identify students’ preferences in feedback type and frequency, given their performance in the experiment. The case representation is conceptualized at the end of this study.

Norzaidah Binti Md. Noh, Rubiyah Yusof, Osamu Ono, Toshiyuki Tojo

Hybrid Agent Tutor Model for e-Learning System with Robotics

In this paper, we propose Hybrid Agent Tutor Model (HATM) simulated with Robotics to enhance an e-Learning system for education field. The hardware robot agents in real world and software agents in virtual one were defined as the Hybrid Agent Tutors (HATs), and will perform interactive relationship so as to support learners to get more efficient educational contents. Based on this concept, we configured a simple prototype system to show flame work according on noble “Qualia” and “Awareness”, and tried to verify the efficiency of this system in e-Learning.

Toshiyuki Tojo, Osamu Ono, Norzaidah Binti Md. Noh, Rubiyah Yusof

Modelling and Control of MacPherson Active Suspension System Using Composite Nonlinear Feedback under Chassis Twisted Road Condition

A ride quality test for active suspension system is real significant in modern automotive suspension control performance validation for ride comfort evaluation


The Composite Nonlinear Feedback (CNF) controller is proposed as a control strategy to reduce the high overshoot on the transient response and fast settling time. The mathematical modeling of a MacPherson quarter car suspension is utilized in this paper. A chassis twists road procedure in ride quality test has been applied. The multi-body dynamics system software so-called CarSim is used for validation. The strength of the proposed control scheme is shown by numerical experiment results and numerical simulation results.

M. Fahezal Ismail, Yahaya Md. Sam, Shahdan Sudin, Kemao Peng, M. Khairi Aripin

General Purpose Simulation

Resource Redistribution after Large Scale Disasters: Case with Gradually Updated Information

The problem of fast supply of affected cites with vital resources after a large scale disaster is under consideration. It is one of the essential components of the short-term recovery characterized by highly probable uncertainty in evaluating the state of damaged region. We propose a general principle by which the required redistribution of vital resources between the affected and neighboring cities can be efficiently implemented under such conditions. The developed principle, first, uses the triage concept determining the current city priority in the resource delivery. Second, it minimizes the delivery time subjected to this priority. Finally a certain plan of the resource redistribution is generated. A particular case when the initial communication system has crashed and formation of a new one and the resource redistribution proceed synchronously is studied numerically. The obtained results enable us to regard the resource redistribution plan governed by the proposed method as semi-optimal and rather efficient especially under uncertainty.

Vasily Lubashevskiy, Taro Kanno, Kazuo Furuta

Gantt Chart Simulation for FAB Scheduling

Capital-intensive facilities called

electronic fabrications

(“FABs” in short) are operated twenty-four hours a day to meet the massive orders on time. The main objectives of scheduling the complex manufacturing process are to meet the on time delivery and to maximize machine utilization. A discrete event simulation approach has brought good results to generate an efficient and practical schedule. However, the approach tends to make short-term decision, which loads any job rather than stays idle. When the setup time is long and the number of crews is limited, being idle could be a better decision than changing jobs. This paper proposes a method to compensate for the limitations of simulation-based schedulers. We propose a Gantt chart simulation approach that formulates WIP level with an

incoming profile

and a

consuming profile

with the number of loaded machines. With two profiles, we can determine when to add or release a machine for each job. The proposed method has been applied to a real factory and showed promising results.

Taedong Kim, Byoung K. Choi, Keyhoon Ko, Donghun Kang

Enterprise Value Portfolio Selection Methodology Using Simulation

In this study, the ‘Value Score Method’ is proposed to evaluate the corporate value portfolio by using values that affect corporate value. Using a simulation analysis, this paper considers the results of six scenarios consisting of various selection criteria (5, 7, 10, 11, 12, 13 point). The performance measurements are the number of selected companies and the ‘rate of return.’ The results indicate that scenario 2 consisting of the 7-point value score displayed the highest rate of return but was identified as having significant difficulty in real world application because many management companies are faced with the problem of specific companies generating this rate of return. Thus, the scenario 3consiting 10 point value is the most realistic scenario and the good rate of return in the model. In addition, scenario 7 was set as the combination of scenario 1 consisting of the 5-point value in the down market and scenario 2 consisting of the 7-point value in the up market. Scenario 7 applied to the intersection of the reference point showed a higher cumulative return of 5,276.2% as compared with scenario 2 with an average of 190.4 companies selected.

Seung-Hwan Gu, Seung-Min Noh, Doo-Suk Kim, Seong-Yong Jang

An Unconventional Unmanned Autonomous Blimp: Design, Modeling and Simulation

In this paper, we present the design and simulation of an unconventional unmanned autonomous blimp. The dynamic model of the tri-ellipsoid blimp is built with mechanism analysis method. Based on dynamic modeling of the blimp, a PID controller against the disturbance during autonomous flight is designed. Simulation results show that the controller is valid with optimal control parameters.

Yi Song, Jingeng Mai, Siqiang Yang, Jiaying Tan, Yan Huang, Qining Wang

Characteristic of Markov Switching Model: An Autoregressive Model

The objective of this paper is to explore the issue of whether the numbers of regimes and variables in aggregate time series are similar to those in individual time series. Equal and value weighted methods of aggregation are considered. A Monte Carlo simulation is carried out with different settings to investigate possible sources of changes those could affect the characteristic of aggregate time series. The results show that the numbers of regimes and variables in aggregate time series is a function of those of individual time series, regardless of the aggregation method. When combining two individual time series (e.g., one series has two regimes and one lag, while another time series has three regimes and one lag), for instance, the numbers of regimes and variables in aggregate time series would be two and one, respectively.

Thatphong Awirothananon


Weitere Informationen

Premium Partner