• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.143-148
• /
• 2024

Traffic congestion has caused issues in various forms such as the environment and economy. Recently, an intelligent transport system (ITS) using artificial intelligence (AI) has been focused so as to alleviate the traffic congestion problem. In this paper, we propose a reinforcement learning-based traffic signal control algorithm that can smooth the flow of traffic while reducing discomfort levels of drivers and pedestrians. By applying the proposed algorithm, it was confirmed that the discomfort levels of drivers and pedestrians can be significantly reduced compared to the existing fixed signal control system, and that the performance gap increases as the number of roads at the intersection increases.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11A
• /
• pp.867-875
• /
• 2003

Current end-to-end congestion control depends only on the information of end points (using three duplicate ACK packets) and generally responds slowly to the network congestion. This mechanism can't avoid TCP global synchronization in which TCP congestion window size is fluctuated during congestion period. Furthermore, if RTT(Round Trip Time) is increased, three duplicate ACK packets are not correct congestion signals because congestion might already disappear and the host may send more packets until it receives three duplicate ACK packets. Recently there are increasing interests in solving end-to-end congestion control using AQM(Active Queue Management) to improve the performance of TCP protocols. AQM is a variation of RED-based congestion control. In this paper, we first evaluate the effectiveness of the current AQM schemes such as RED, CHOKe, ARED, FRED and SRED, over traffic with different rates and over traffic with mixed responsive and non-responsive flows, respectively. In particular, CHOKe mechanism shows greater unfairness, especially when more unresponsive flows exist in a shared link. We then propose a new AQM scheme using CHOKe mechanism, called DQC(Double Queue CHOKe), which uses two FIFO queues before applying CHOKe mechanism to adaptive congestion control. Simulation shows that it works well in protecting congestion-sensitive flows from congestion-causing flows and exhibits better performances than other AQM schemes. Also we use partial state information, proposed in LRURED, to improve our mechanism.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.310-323
• /
• 2004

In this paper, we extend the multiple time scale control framework to window-based congestion control, in particular, TCP This is performed by interfacing TCP with a large tine scale control nodule which adjusts the aggressiveness of bandwidth consumption behavior exhibited by TCP as a function of "large time scale" network state. i.e., conformation that exceeds the horizon of the feedback loop as determined by RTT Our contribution is threefold. First, we define a modular extension of TCP-a function call with a simple interface-that applies to various flavors of TCP-e.g., Tahoe, Reno, Vegas and show that it significantly improves performance. Second, we show that multiple time scale TCP endows the underlying feedback control with preactivity by bridging the uncertainty gap associated with reactive controls which is exacerbated by the high delay-bandwidth product in broadband wide area networks. Third, we investigate the influence of three traffic control dimensions-tracking ability, connection duration, and fairness-on performance. Performance evaluation of multiple time scale TCP is facilitated by a simulation bench-mark environment which is based on physical modeling of self-similar traffic.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.285-289
• /
• 2004

Recently, due to the high development of the internet, needs for multimedia streams such as digital audio and video is increasing much more. In case of transmitting multimedia streams using the User Datagram Protocol (UDP), it may cause starvation of TCP traffic on the same transmission path, thus resulting in congestion collapse and enormous delay because UDP does not perform TCP-like congestion control. Because of this problem, diverse researches are being conducted on new transmission schemes and protocols intended to efficiently reduce the transmission delay of real-time multimedia streams and perform congestion control. The TCP-friendly congestion control schemes can be classified into the window-based congestion control, which uses the general congestion window management function, and the rate-based congestion control, which dynamically adjusts transmission rate by using TCP modeling equations and the like. In this paper, we suggest the square-root congestion avoidance algorithm with the hybrid TCP-friendly congestion control scheme which the window-based and rate-based congestion controls are dealt with in a combined way. We apply the proposed algorithm to the existing TEAR. We simulate the performance of the proposed TEAR by using NS, and the result shows that it gives better improvement in the stability needed for providing congestion control than the existing TEAR.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.1 no.2
• /
• pp.102-109
• /
• 2006

In this paper, we improve the performance of bidirectional TCP connection over end-to-end network that uses transfer rate-based flow and congestion control. The sharing of a common buffer by TCP packets and acknowledgement has been known to result in an effect called ack compression, where acks of a connection arrive at the source bunched together, resulting in unfairness and degraded throughput. The degradation in throughput due to bidirectional traffic can be significant. For example, even in the simple case of symmetrical connections with adequate window size, the connection efficiency is improved about 20% for three levels of background traffic 2.5Mbps, 5.0Mbps and 7.5Mbps. Otherwise, the throughput of jitter is reduced about 50% because round trip delay time is smaller between source node and destination node. Also, we show that throughput curve is improved with connection rate algorithm which is proposed for TCP congestion avoidance as a function of aggressiveness threshold for three levels of background traffic 2.5Mbps, 5Mbps and 7.5Mbps.

• Journal of Korean Society of Transportation
• /
• v.5 no.2
• /
• pp.81-95
• /
• 1987

In line with the continued growth of car ownership, the traffic problems in central area of metropoles such as Seoul would become increasingly degraded. comparing with most western cities, the problems in Seoul are characterized by the improportionately high rates of intersection delay, station congestion, traffic accidents caused by weaving conflicts and pedestrian congestion. It is caused by the lack of flexibility I street network, which is prerequisite for upholding the efficacy of traffic management and control, resulted from the simplicity of network graph in terms of connectivity, street density and distribution by width. This pattern has been resulted from the prolonged policy pursuing the street-widening of the nagging bottleneck in such a short period since the 1950s, comparing that most western cities had undergone over several centuries an age of horse-and-vehicle transportation. In order to improve the expected traffic problems in central area over the coming periods of motorization, it is imperative to restructure the street network in Central Seoul so that the efficacy of traffic management and control may be operative. Based upon the long-range planning the street network should be restructured by stages so that cenral traffic may be controled by one-way operation and most through-traffic be detoured around fringe area.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.99-102
• /
• 2001

It has well known that the congestion of traffic and it's distribution. There are very important problems in the traffic control systems. In this paper, we will purpose an ITFS(Intelligent Traffic Forecasting System) which can determine the car classes and transport them to ITS(Intelligent Traffic control System). The system will be used the Inductive Loop Detector(ILD)and the Fuzzy logic and shown the effectiveness by the computer simulation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1B
• /
• pp.29-40
• /
• 2004

In this paper, we propose a new early congestion detection and notification technique called QR-AQM. Unlike RED and it's variation, QR-AQM measures the total traffic rate from TCP sessions, predicts future network congestion, and determine the packet marking probability based on the measured traffic rate. By incorporating the traffic rate in the decision process of the packet marking probability, QR-AQM is capable of foreseeing future network congestion as well as terminating congestion resolution procedure in much more timely fashion than RED. As a result, simulation results show that QR-AQM maintains the buffer level within a fairly narrow range around a target buffer level that may be selected arbitrarily as a control parameter. Consequently, compared to RED and its variations, QR-AQM is expected to significantly reduce the jitter and delay variance of packets traveling through the buffer while achieving nearly identical link utilization.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.7
• /
• pp.3176-3183
• /
• 2011

Traffic and congestion control in the wireless sensor network is an important parameter that decides the throughput and QoS (Quality of Service). This paper proposes a transmission rate priority-based traffic control scheme to serve digital contents streaming in wireless sensor networks. In this paper, priority for transmission rate decides on the real-time traffic and non-real-time with burst time and length. This transmission rate-based priority creates low latency and high reliability so that traffic can be efficiently controlled when needed. Traffic control in this paper performs the service differentiation via traffic detection process, traffic notification process and traffic adjustment. The simulation results show that the proposed scheme achieves improved performance in delay rate, packet loss rate and throughput compared with those of other existing CCF and WCA.