• 응용통계연구
• /
• 제24권2호
• /
• pp.307-313
• /
• 2011

본 연구에서는 인터넷 트래픽 자료를 예측하는데 사용되는 Holt-Winters, FARIMA, AR-GARCH 모형을 트래픽 예측에 적용하여 각 모형을 성능을 비교하고자 한다. 각 시계열 모형에 대해 소개하고, 트래픽 자료의 특성인 장기기억 특성을 설명하는데 적합한 모형을 알아보기 위해 실제 트래픽 자료에 적용하여 예측 성능을 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권1호
• /
• pp.216-238
• /
• 2023

In intelligent transportation systems, traffic management is an important task. The accurate forecasting of traffic characteristics like flow, congestion, and density is still active research because of the non-linear nature and uncertainty of the spatiotemporal data. Inclement weather, such as rain and snow, and other special events such as holidays, accidents, and road closures have a significant impact on driving and the average speed of vehicles on the road, which lowers traffic capacity and causes congestion in a widespread manner. This work designs a model for multivariate short-term traffic congestion prediction using SLSTM_AE-BiLSTM. The proposed design consists of a Bidirectional Long Short Term Memory(BiLSTM) network to predict traffic flow value and a Convolutional Neural network (CNN) model for detecting the congestion status. This model uses spatial static temporal dynamic data. The stacked Long Short Term Memory Autoencoder (SLSTM AE) is used to encode the weather features into a reduced and more informative feature space. BiLSTM model is used to capture the features from the past and present traffic data simultaneously and also to identify the long-term dependencies. It uses the traffic data and encoded weather data to perform the traffic flow prediction. The CNN model is used to predict the recurring congestion status based on the predicted traffic flow value at a particular urban traffic network. In this work, a publicly available Caltrans PEMS dataset with traffic parameters is used. The proposed model generates the congestion prediction with an accuracy rate of 92.74% which is slightly better when compared with other deep learning models for congestion prediction.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권1호
• /
• pp.144-150
• /
• 2020

Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2003년도 추계종합학술대회
• /
• pp.837-840
• /
• 2003

최근 인터넷의 발전으로 디지털 오디오 및 비디오와 같은 멀티미디어 스트리밍에 대한 요구가 증가하고 있다. 이러한 멀티미디어 스트리밍을 위해 UDP로 전송할 경우 TCP와 같은 혼잡제어를 수행하지 않기 때문에 동일한 경로에 TCP 트래픽 궁핍을 일으켜 혼잡붕괴를 초래한다. 이러한 역효과를 피하기 위해 멀티미디어 스트리밍을 위한 새로운 전송 프로토콜에 대한 연구가 수행되고 있다. TCP 친화적 혼잡제어기법은 크게 일반적인 혼잡윈도우 관리기능을 이용하는 윈도우기반 혼잡제어(window-based congestion control)와 TCP 모델링 방정식 등을 이용하여 전송율을 직접 조절하는 율기반 혼잡제어(rate-based congestion control)로 나눌 수 있다. 본 논문은 윈도우기반과 율기반을 복합적으로 다룬 하이브리드 TCP-friendly 혼잡제어기법에서 전송을 개선을 위한 알고리즘을 제안하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제8권4호
• /
• pp.1-10
• /
• 2016

This paper considers WiMedia UWB network based wireless ship area network (WSAN) so as to support high-quality multimedia video data services and important shipboard control data. In this paper, prioritized contention access (PCA) and distributed reservation protocol (DRP) based on WiMedia UWB (ECMA-368) MAC protocols are combined and proposed to support mixed high-quality video traffic and shipboard control data traffic applying varying DRP and PCA data periods according to channel condition and link parameter ptimization. It is shown that the proposed dynmaic channel allocation of WiMedia UWB MAC protocol can provide reliable mixed video and shipboard control data traffic as well.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.582-585
• /
• 2018

교통량이 증가하고 도로 네트워크가 복잡해짐에 따라 정확한 교통 흐름 파악을 통해 교통의 원활한 흐름을 유도하는 것은 많은 국가의 관심사항이다. 교통 흐름을 효과적으로 알기 위한 다양한 분석 기술 및 연구들이 있어 왔지만 위치(GPS) 데이터를 포함한 데이터 시각화를 통해 먼저 교통 흐름의 패턴을 찾는 것이 필요하다. 본 논문에서는 실제 도시의 교통 궤적을 시뮬레이션한 내용을 도구로 사용함으로써 교통 흐름의 패턴을 시각화하는 것을 목표로 한다. 이에 24시간운행 되어 지고 정해진 경로가 없는 특징을 가진 실제 택시 40대에 센서 모듈을 설치하여 IoV(Internet of Vehicle)데이터를 수집하고 이 데이터를 이용하여 전처리 과정을 거친 후 오픈소스 기반의 데이터 시각화 도구를 우리의 데이터 특성에 적합하도록 개선하였다. 해당 시각화 모델은 시간 흐름에 따른 차량 트랙킹 Dot을 통해 차량 밀집 지역과 이동 경로 패턴 인식이 가능하므로 도시 내에서 또는 도시와 도시간의 교통 흐름 파악을 통해 도시 환경 문제 개선에 기여할 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권3호
• /
• pp.872-885
• /
• 2015

The rapid increase of smart mobile devices and mobile applications has led to explosive growth of data traffic in cellular network. Offloading data traffic becomes one of the most urgent technical problems. Recent work has proposed to exploit opportunistic communications to offload cellular traffic for mobile data dissemination services, especially for accepting large delayed data. The basic idea is to deliver the data to only part of subscribers (called target-nodes) via the cellular network, and allow target-nodes to disseminate the data through opportunistic communications. Human mobility shows temporal and spatial characteristics and predictability, which can be used as effective guidance efficient opportunistic communication. Therefore, based on the regularity of human mobility we propose NodeRank algorithm which uses the encounter characteristics between nodes to choose target nodes. Different from the existing work which only using encounter frequency, NodeRank algorithm combined the contact time and inter-contact time meanwhile to ensure integrity and availability of message delivery. The simulation results based on real-world mobility traces show the performance advantages of NodeRank in offloading efficiency and network redundant copies.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.361-362
• /
• 2007

This paper presents the Traffic information system that based on an embedded WinCE board which has GPS and HSDPA. This system is able to overcome the limit of area using the Internet service which other systems can't provide. When the embedded board receives data about the geometric and vehicle speed information, it transmits to the server via HSDPA/the Internet. The server receives and processes it for the path services. And also we present the path guidance algorithm which is based on the speed information. These algorithm responses to the dynamical traffic condition through updating traffic information. Especially, we suggest a Traffic Status Variable in each branch which represents each road's traffic status. This Traffic Status Variable contains speed, road grade; we separate the road three groups as speed limitation; and past speed data - for example, week day rush hour of each road. In addition, the data of cross about left-turn or right-turn can update. Those elements is consisted Traffic Status Variable.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권1호
• /
• pp.240-259
• /
• 2020

Analyzing network traffic is the basis of dealing with network security issues. Most of the network security systems depend on the feature selection of network traffic data and the detection ability of malicious traffic in network can be improved by the correct method of feature selection. An FAFS method, which is short for Fuzzy Association Feature Selection method, is proposed in this paper for network malicious traffic detection. Association rules, which can reflect the relationship among different characteristic attributes of network traffic data, are mined by association analysis. The membership value of association rules are obtained by the calculation of fuzzy reasoning. The data features with the highest correlation intensity in network data sets are calculated by comparing the membership values in association rules. The dimension of data features are reduced and the detection ability of malicious traffic detection algorithm in network is improved by FAFS method. To verify the effect of malicious traffic feature selection by FAFS method, FAFS method is used to select data features of different dataset in this paper. Then, K-Nearest Neighbor algorithm, C4.5 Decision Tree algorithm and Naïve Bayes algorithm are used to test on the dataset above. Moreover, FAFS method is also compared with classical feature selection methods. The analysis of experimental results show that the precision and recall rate of malicious traffic detection in the network can be significantly improved by FAFS method, which provides a valuable reference for the establishment of network security system.

• 한국통신학회논문지
• /
• 제35권4B호
• /
• pp.576-583
• /
• 2010

무선인터넷은 이동 단말기를 통해 무선으로 인터넷에 접속하여 데이터 통신이나 인터넷 서비스를 제공받을 수 있는 네트워크이다. 무선 접속망과 유선 인터넷의 다른 두 네트워크를 효율적으로 연동하기 위해서는 프로토콜 전환 시스템인 WAP게이트웨이가 필요하다. 무선인터넷 서비스를 안정적이고 비용 효율적으로 제공하기 위해서는 적절한 게이트웨이 시스템 용량산출이 필요하고 시설투자의 경제성을 획득하기 위해서는 트래픽 모델링 및 예측을 포함한 트래픽 엔지니어링 기법이 필요하다. 기존의 용량산출 기법은 직관적이고 정성적인 방식을 탈피하지 못했으나 본 논문에서는 보다 정량적이며 해석적으로 WAP 서비스에서 트래픽 기술 파라미터 정의하고 트래픽 예측 기법에 근거한 용량산출 기법을 다룬다.