• Journal of Computing Science and Engineering
• /
• 제1권1호
• /
• pp.31-55
• /
• 2007

Contemporary end-servers and network-routers rely on traffic shaping to deal with server overload and network congestion. Although such traffic shaping provides a means to mitigate the effects of server overload and network congestion, the lack of cooperation between end-servers and network-routers results in waste of network resources. To remedy this problem, we design, implement, and evaluate NetDraino, a novel mechanism that extends the existing queue-management schemes at routers to exploit the link congestion information at downstream end-servers. Specifically, NetDraino distributes the servers' traffic-shaping rules to the congested routers. The routers can then selectively discard those packets-as early as possible-that overloaded downstream servers will eventually drop, thus saving network resources for forwarding in-transit packets destined for non-overloaded servers. The functionality necessary for servers to distribute these filtering rules to routers is implemented within the Linux iptables and iproute2 architectures. Both of our simulation and experimentation results show that NetDraino significantly improves the overall network throughput with minimal overhead.

• 산업공학
• /
• 제23권4호
• /
• pp.349-356
• /
• 2010

The role of Intelligent Transportation System (ITS) is to efficiently manipulate the traffic flow and reduce the cost in logistics by using the state of the art technologies which combine telecommunication, sensor, and control technology. Especially, the hardware part of ITS is rapidly adapting to the up-to-date techniques in GPS and telematics to provide essential raw data to the controllers. However, the software part of ITS needs more sophisticated techniques to take care of vast amount of on-line data to be analyzed by the controller for their decision makings. In this paper, the authors develop a traffic congestion prediction model based on several different parameters from the sensory data captured in the Vehicle Detection System (VDS). This model uses the neural network technology in analyzing the traffic flow and predicting the traffic congestion in the designated area. This model also validates the results by analyzing the errors between actual traffic data and prediction program.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2483-2503
• /
• 2016

Traffic congestion is a severe problem in many modern cities around the world. Real-time and accurate traffic congestion identification can provide the advanced traffic management systems with a reliable basis to take measurements. The most used data sources for traffic congestion are loop detector, GPS data, and video surveillance. Video based traffic monitoring systems have gained much attention due to their enormous advantages, such as low cost, flexibility to redesign the system and providing a rich information source for human understanding. In general, most existing video based systems for monitoring road traffic rely on stationary cameras and multiple vehicle tracking method. However, most commonly used multiple vehicle tracking methods are lack of effective track initiation schemes. Based on the motion of the vehicle usually obeys constant velocity model, a novel vehicle recognition method is proposed. The state of recognized vehicle is sent to the GM-PHD filter as birth target. In this way, we relieve the insensitive of GM-PHD filter for new entering vehicle. Combining with the advanced vehicle detection and data association techniques, this multiple vehicle tracking method is used to identify traffic congestion. It can be implemented in real-time with high accuracy and robustness. The advantages of our proposed method are validated on four real traffic data.

• 대한교통학회지
• /
• 제24권3호
• /
• pp.29-37
• /
• 2006

도시고속도로의 반복정체는 발생시점과 지점이 거의 일정하므로 정체발생 예상 및 사전대응을 통한 효과적인 관리가 가능하다. 기존의 교통관리시스템에서는 패턴데이터를 이용하여 반복정체를 관리하고자하였으나 다변하는 도시 부교통에서는 적용하기 어려운 경우가 많았다. 본 논문에서는 반복정체 발생확률을 통계적 분포를 적용한 통행속도별 발생확률을 이용하여 구하고자 하였다. 반복정체 발생확률 추정을 통해 반복정체 발생시점 및 지속시간을 파악하고, 효과적인 사전대응 수립과 교통운영이 가능할 것으로 기대된다

• 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.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2002년도 춘계학술대회
• /
• pp.121-127
• /
• 2002

In this paper, we propose traffic management support and evaluate the performance through simulation. We suggest traffic management routing protocol that can guarantee reliance according to not only reduction of the Network traffic congestion but also distribution of the network load that prevents data transmission. For performance evaluation, we analyzed the average data reception rate and network load, considering the node mobility. We found that in the mobile Ad Hoc networks, the traffic management service increased the average data reception rate and reduced the network traffic congestion and network load in Mobile Ad Hoc Networks.

• 한국컴퓨터정보학회논문지
• /
• 제15권11호
• /
• pp.135-142
• /
• 2010

프록시 시스템에서의 QoS는 혼잡 (congestion), 지연 (delay), 재전송 (retransmission) 등과 같은 간섭에 의해 많은 영향을 받는다. 또한 멀티-레벨 스트리밍 서비스는 시간 동기화에 의해 영향을 받으며, 이로 인하여 서비스 성능이 저하된다. 본 논문에서는 프록시 시스템에서 발생하는 스트리밍 서비스의 성능 저하를 개선하고 스트리밍 처리율을 향상시키기 위한 세그먼트 기반의 버퍼 관리 메커니즘을 제안한다. 제안된 논문의 목적은 다음과 같다. 1) 세그먼트 기반의 버퍼관리 메커니즘을 이용하여 다중 스트리밍 서비스를 최적화한다. 2) 혼잡, 간섭 등으로 인해 발생되는 오버헤드를 줄인다. 3) 끊김 현상, 지연 등으로 인해 발생하는 재전송의 문제를 최소화한다. 이러한 목적을 수행하기 위해 우리는 퍼지 값 $\mu$와 비용 가중치 $\omega$를 이용한다. 시뮬레이션 결과 제안된 메커니즘은 버퍼 캐시 제어율, 평균 패킷 손실률, 그리고 스트림 적합성 척도에 따른 지연 절약율에 있어서 기존의 고정길이 세그먼트기법, 피라미드 (pyramid) 세그먼트 기법, 그리고 스카이스크렙퍼 (skyscraper) 세그먼트 기법보다 성능이 효율적임을 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 추계학술대회 논문집 학회본부 A
• /
• pp.6-9
• /
• 2000

This paper presents the detailed derivation of optimal nodal price for active power to regionally evaluate system loss and congestion cost. The method is to decompose them into different components corresponding to system loss, transmission congestion, voltage constraint, and so on. The decomposed information for nodal price can be used to provide economic signals for generation or transmission investment as well as to improve the efficient usage of power grid and congestion management. The result of case study on IEEE 30 bus system is reported to illustrate the proposed method.

• 대한전기학회논문지:전력기술부문A
• /
• 제54권12호
• /
• pp.567-572
• /
• 2005

This paper presents a scheme to design optimal placement of phase-shifting transformers for power system congestion problems. A good design of phase-shifting transformers placement can improve total transfer capability in interconnected systems. In order to find the optimal placement of phase-shifting transformers, the power flows of the interesting transmission lines are evaluated using sequential quadratic programming technique. This algorithm considers power balance equations and security constraints such as voltage magnitudes and transmission line capacities. The proposed scheme is tested in 10 machines 39 buses and IEEE 57 buses systems. Test result shows that the proposed method can find the optimal placement of phase-shifting transformers to solver power system congestion problems.

• 전자공학회논문지 IE
• /
• 제43권3호
• /
• pp.41-48
• /
• 2006

본 논문에서는 인터넷 트래픽 입력율의 예측성을 이용하여 큰 시간 스케일 (large time scale)에서 트래픽 입력율 예측을 통한 새로운 동적 큐 관리 기법 (Active Queue Management (AQM))을 제안한다. RED를 비롯한 대부분의 기존 AQM 기법들은 큐 길이를 기반으로 망의 혼잡 정도를 판단하여 패킷 폐기 확률을 설정하고 이에 따라 입력 패킷을 폐기하므로 동적으로 변화하는 망 환경에 제어 인자들이 적절히 적응하지 못하거나 적응시간이 긴 단점을 가진다. 제안 기법은 패킷 측정을 통해 얻은 입력율 정보를 자기 회기 (Auto-Regressive (AR)) 시 계열 모델에 적용하여 향후 트래픽 입력율을 예측하고, 이를 기반으로 향후 망 혼잡 수준을 결정한다. 혼잡이 예측되는 경우 향후 트래픽 입력율이 라우터의 서비스율과 근사하도록 패킷 폐기 확률을 결정함으로써 제안 기법은 패킷 폐기율은 기존 기법과 유사하게 유지하면서 링크 효율을 높이고 평균 큐 길이를 망 환경변화에 무관하게 안정적으로 유지할 수 있게 해준다. 본 논문에서는 ns-2 시뮬레이터를 이용하여 제안기법과 RED, adaptive RED (ARED), REM, Predictive AQM (PAQM)과의 성능 비교를 통해 다양하게 변화하는 망 환경에서 제안기법의 성능이 평균 큐 길이와 망 적응성 측면에서 우수하다는 사실을 검증하였다.