• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.465-466
• /
• 2009

This paper investigates congestion detection and control strategies for multi-path traffic (CDCM) diss emination in lifetime-constrained wireless sensor networks. CDCM jointly exploits packet arrival rate, succ essful packet delivery rate and current buffer status of a node to measure the congestion level. Our objec tive is to develop adaptive traffic rate update policies that can increase the reliability and the network lif etime. Our simulation results show that the proposed CDCM scheme provides with good performance.

• Journal of Drive and Control
• /
• v.14 no.3
• /
• pp.8-17
• /
• 2017

With automobiles sharply increasing in numbers worldwide, we are faced with critical social issues such as traffic accidents, traffic jams, environmental pollution, and economic inefficiency. In response, research on ITS is promoted mainly by regions with advanced automotive industry such as the U.S., Europe, and Japan. While Korea is working on moving forward in the global market through developing and turning to global standards systems related to ASV (Advanced Safety Vehicle), the country is not fully prepared for such projects. The purpose of ACC (Adaptive Cruise Control) is to control a vehicle's longitudinal speed and distance and minimize driver workload. Such a system should be valuable in preventing accidents, as it reduces driver workload in the 21st-century world of telematics created by development of the automobile culture industry. In this light, the thesis presents a method to test and evaluate ACC system and a mathematical method to assess distance. For the proposed test and evaluation, theoretical values are tested with vehicle test and a database is acquired, by using vehicles equipped with an ACC system. Theoretical evaluation criteria for developing ACC system may be used and scenario-specific evaluation methods may find useful application through testing the formula proposed by comparing the database and mathematical method.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.91-93
• /
• 2009

In this paper, we present the Q-learning method for adaptive traffic signal control on the basis of In this paper, we present the Q-learning method for adaptive traffic signal control on the basis of multi-agent technology. The structure is composed of sixphase agents and one intersection agent. Wireless communication network provides the possibility of the cooperation of agents. As one kind of reinforcement learning, Q-learning is adopted as the algorithm of the control mechanism, which can acquire optical control strategies from delayed reward; furthermore, we adopt dynamic learning method instead of static method, which is more practical. Simulation result indicates that it is more effective than traditional signal system.

• Journal of Communications and Networks
• /
• v.12 no.3
• /
• pp.253-265
• /
• 2010

The problem of pricing for a telecommunication network is investigated with respect to the users' sensitivity to the pricing structure. A functional optimization problem is formulated, in order to compute price reallocations as functions of data collected in real time during the network evolution. No a-priori knowledge about the users' utility functions and the traffic demands is required, since adaptive reactions to the network conditions are sought in real time. To this aim, a neural approximation technique is studied to exploit an optimal pricing control law, able to counteract traffic changes with a small on-line computational effort. Owing to the generality of the mathematical framework under investigation, our control methodology can be generalized for other decision variables and cost functionals.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.735-738
• /
• 1997

The traffic congestion caused by the exploding increase of vehicles became one of the severest social problems. Among the various approaches to solve this problem, controlling the length of traffic signals appropriately according to the individual traffic situation would be the most plausible and cost-effective method. To design a traffic signal controller which has such a property as adaptive decision-making process, we adopt fuzzy logic control method(fuzzy traffic signal controller), Moreover, using genetic algorithms we obtain an optimized fuzzy traffic signal controller (GA-fuzzy traffic signal controller). To evaluate and validate the proposed fuzzy and GA-fuzzy traffic signal controller, simulation results are presented.

• The KIPS Transactions:PartC
• /
• v.8C no.1
• /
• pp.51-59
• /
• 2001

In order to support various QoS, IETF has proposed the Differentiated Services Model which provides discrimination service according to t the user’s requirements and payment intention intention for each traffic characteristic. This model is an excellent mechanism, which is not too c complicated in terms of the management for service and network model. Also, it has scalability that satisfies the requirement of Differentiated Services. In this paper, We define the Differentiated Services Model using feedback control, propose its control procedure, and analyze its p performance. In conventional model, non-adaptive traffic, such as UDP traffic, is more occupied the network resource than adaptive traffic, such a as TCP traffic. On the other hand, the Differentiated Services Model using feedback control fairly utlizes the network resources and even p prevents congestion occurrence due to its ability of congestion expectation.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.94-96
• /
• 2009

In this paper, we present the Q-learning method for adaptive traffic signal control on the basis of multi-agent technology. The structure is composed of sixphase agents and one intersection agent. Wireless communication network provides the possibility of the cooperation of agents. As one kind of reinforcement learning, Q-learning is adopted as the algorithm of the control mechanism, which can acquire optical control strategies from delayed reward; furthermore, we adopt dynamic learning method instead of static method, which is more practical. Simulation result indicates that it is more effective than traditional signal system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11B
• /
• pp.1038-1049
• /
• 2003

Exactly measuring traffic load is the basis for efficient traffic engineering. However, precise traffic measurement involves inspecting every packet traversing a lint resulting in significant overhead on routers with high-speed links. Sampling techniques are proposed as an alternative way to reduce the measurement overhead. But, since sampling inevitably accompany with error, there should be a way to control, or at least limit, the error for traffic engineering applications to work correctly. In this paper, we address the problem of bounding sampling error within a pre-specified tolerance level. We derive a relationship between the number of samples, the accuracy of estimation and the squared coefficient of variation of packet size distribution. Based on this relationship, we propose an adaptive random sampling technique that determines the minimum sampling probability adaptively according to traffic dynamics. Using real network traffic traces, we show that the proposed adaptive random sampling technique indeed produces the desired accuracy, while also yielding significant reduction in the amount of traffic samples.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4268-4289
• /
• 2020

Advanced traffic signal timing method plays very important role in reducing road congestion and air pollution. Reinforcement learning is considered as superior approach to build traffic light timing scheme by many recent studies. It fulfills real adaptive control by the means of taking real-time traffic information as state, and adjusting traffic light scheme as action. However, existing works behave inefficient in complex intersections and they are lack of feasibility because most of them adopt traffic light scheme whose phase sequence is flexible. To address these issues, a novel adaptive traffic signal timing scheme is proposed. It's based on actor-critic reinforcement learning algorithm, and advanced techniques proximal policy optimization and generalized advantage estimation are integrated. In particular, a new kind of reward function and a simplified form of state representation are carefully defined, and they facilitate to improve the learning efficiency and reduce the computational complexity, respectively. Meanwhile, a fixed phase sequence signal scheme is derived, and constraint on the variations of successive phase durations is introduced, which enhances its feasibility and robustness in field applications. The proposed scheme is verified through field-data-based experiments in both medium and high traffic density scenarios. Simulation results exhibit remarkable improvement in traffic performance as well as the learning efficiency comparing with the existing reinforcement learning-based methods such as 3DQN and DDQN.

• The KIPS Transactions:PartC
• /
• v.9C no.5
• /
• pp.783-788
• /
• 2002

Adaptive Cyclic Packet Dropping algorithm (ACPD), and Non-adaptive Cyclic Packet Dropping algorithm (NCPD) are applying stricter drop precedence than that of RIO algorithm. Especially, the ACPD algorithm drops adaptively packets for the congestion control, as predicting traffic pattern between each cycle. Therefore the ACPD algorithm makes up for the drawback of RIO algorithm and minimizes the wastes of the bandwidth being capable of predicting in the NCPD algorithm. And we executed a simulation and analyzed the throughput and packet drop rate based on Sending Priority changing dynamically depending on network traffic. In this algorithm, applying strict drop precedence policy, we get better performance on priority levels. The results show that the proposed algorithms may provide more efficient and stricter drop precedence policy as compared to RIO independent of traffic load. The ACPD algorithm can provide better performance on priority levels and keep stricter drop policy than RIO and the NCPD algorithm.