• The KIPS Transactions:PartC
• /
• v.13C no.5 s.108
• /
• pp.559-566
• /
• 2006

Virus throttling technique, one of many early worm detection techniques, detects the Internet worm propagation by limiting the connect requests within a certain ratio. The typical virus throttling detects worm occurrence by monitoring the length of delay queue with the fixed period of rate limiter. In this paper, we propose an algorithm that controls the period of rate limiter autonomically by utilizing the weighted average delay queue length and suggest various period determination policies that use the weighted average delay queue length as an input parameter. Through deep experiments, it is verified that the proposed technique is able to lessen inconvenience of users by reducing the connection delay time with haying just little effect on worm detection time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.3
• /
• pp.59-72
• /
• 2017

As the part of study which handles the measure to use the individual vehicle information of taxi GPS data on signal controls in order to overcome the limitation of Loop detector-based collecting methods of real-time signal control system, this paper conducted series of evaluations and improvements on link travel time, queue vehicle time estimates and traffic condition decision algorithm from the research introduced in 2016. considering the control group and the other, the link travel time has enhanced the travel time and the length of queue vehicle has enhanced the estimated model taking account of the traffic situation. It is analyzed that the accuracy of the average link travel time and the length of queue vehicle are respectably both approximately 95 % and 85%. The traffic condition decision algorithm reflected the improved travel speed and vehicle length. Smoothing was performed to determine the trend of the traffic situation and reduce the fluctuation of the data, and the algorithms have refined so as to reflect the pass period on overflow judgment criterion.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.2
• /
• pp.39-57
• /
• 2018

The purpose of this study was to construct an artificial intelligence model that learns and estimates the relationship between vehicle queue length and link travel time in urban areas. The vehicle queue length estimation model is modeled by three models. First of all, classify whether vehicle queue is a link overflow and estimate the vehicle queue length in the link overflow and non-overflow situations. Deep learning model is implemented as Tensorflow. All models are based DNN structure, and network structure which shows minimum error after learning and testing is selected by diversifying hidden layer and node number. The accuracy of the vehicle queue link overflow classification model was 98%, and the error of the vehicle queue estimation model in case of non-overflow and overflow situation was less than 15% and less than 5%, respectively. The average error per link was about 12%. Compared with the detecting data-based method, the error was reduced by about 39%.

• The KIPS Transactions:PartC
• /
• v.12C no.6 s.102
• /
• pp.847-854
• /
• 2005

Since the propagation speed of the Internet worms is quite fast, worm detection in early propagation stage is very important for reducing the damage. Virus throttling technique, one of many early worm detection techniques, detects the Internet worm propagation by limiting the connection requests within a certain ratio.[6, 7] The typical throttling technique increases the possibility of false detection by treating destination IP addresses independently in their delay queue managements. In addition, it uses a simple decision strategy that determines a worn intrusion if the delay queue is overflown. This paper proposes a two dimensional delay queue management technique in which the sessions with the same destination IP are linked and thus a IP is not stored more than once. The virus throttling technique with the proposed delay queue management can reduce the possibility of false worm detection, compared with the typical throttling since the proposed technique never counts the number of a IP more than once when it chicks the length of delay queue. Moreover, this paper proposes a worm detection algorithm based on weighted average queue length for reducing worm detection time and the number of worm packets, without increasing the length of delay queue. Through deep experiments, it is verified that the proposed technique taking account of the length of past delay queue as well as current delay queue forecasts the worn propagation earlier than the typical iuぉ throttling techniques do.

• Journal of Internet of Things and Convergence
• /
• v.10 no.3
• /
• pp.19-24
• /
• 2024

Recent advances in large-scale data processing technologies such as big data, cloud computing, and artificial intelligence have increased the demand for high-performance storage devices in data centers and enterprise environments. In particular, the fast data response speed of storage devices is a key factor that determines the overall system performance. Solid state drives (SSDs) based on the Non-Volatile Memory Express (NVMe) interface are gaining traction, but new bottlenecks are emerging in the process of handling large data input and output requests from multiple hosts simultaneously. SSDs typically process host requests by sequentially stacking them in an internal queue. When long transfer length requests are processed first, shorter requests wait longer, increasing the average response time. To solve this problem, data transfer timeout and data partitioning methods have been proposed, but they do not provide a fundamental solution. In this paper, we propose a dual queue based scheduling scheme (DQBS), which manages the data transfer order based on the request order in one queue and the transfer length in the other queue. Then, the request time and transmission length are comprehensively considered to determine the efficient data transmission order. This enables the balanced processing of long and short requests, thus reducing the overall average response time. The simulation results show that the proposed method outperforms the existing sequential processing method. This study presents a scheduling technique that maximizes data transfer efficiency in a high-performance SSD environment, which is expected to contribute to the development of next-generation high-performance storage systems

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.3
• /
• pp.177-183
• /
• 2007

Active queue management (AQM) refers to a family of packet dropping mechanisms for router queues that has been proposed to support end-to-end congestion control mechanisms in the Internet. The proposed AQM algorithm by the IETF is Random Early Detection (RED). The RED algorithm allows network operators simultaneously to achieve high throughput and low average delay. However. the resulting average queue length is quite sensitive to the level of congestion. In this paper, we propose the Refined Adaptive RED(RARED), as a solution for reducing the sensitivity to parameters that affect RED performance. Based on simulations, we observe that the RARED scheme improves overall performance of the network. In particular, the RARED scheme reduces packet drop rate and improves goodput.

• Journal of Korean Society of Transportation
• /
• v.22 no.3 s.74
• /
• pp.85-94
• /
• 2004

Loop detection systems have been used in real-time signal control system to collect traffic information for estimating queue lengths. The queue length algorithm uses speed as a key variable estimated from occupancy time and average vehicle length. The measurement of average vehicle length is affected from the lengths of feeder cable, but their effects have not yet been evaluated. In this study, the variability of average vehicle length due to the lengths of feeder cable is assessed through a field study, and a practical guidelines is proposed. By applying this result, the operational performance of real-time signal control system could be improved.

• IE interfaces
• /
• v.25 no.3
• /
• pp.283-289
• /
• 2012

M/G/1 queue with server vacations period depending on the previous vacation and customer's arrival is considered. Most existing studies on M/G/1 queue with server vacations assume that server vacations are independent of customers' arrival. However, some vacations are terminated by some class of customers' arrival in certain queueing systems. In this paper, therefore, we investigate M/G/1 queue with server vacations where each vacation period has different distribution and vacation length is influenced by customers' arrival. Laplace-Stieltjes transform of the waiting time distribution and the distribution of number of customers waiting for each class of customers are respectively derived. As performance measures, mean waiting time and average number of customers waiting for each class of customers are also derived.

• The KIPS Transactions:PartC
• /
• v.11C no.1
• /
• pp.89-98
• /
• 2004

AQM (Active Queue Management) techniques such as RED (Random Early Detection) which be proposed to solve the congestion of internet perform congestion control effectively for TCP data. However, in the situation where TCP and UDP share the bottleneck link, they can not solve the problems of the unfairness and long queueing delay. In this paper, we proposed an simple queue management algorithm, called PSRED (Protocol Sensitive RED), that improves fairness and decreases queueing delay. PSRED algorithm improves fairness and decreases average queue length by distinguishes each type of flow in using protocol field of packets and applies different drop functions to them respectively.

• 전자공학회논문지 IE
• /
• v.43 no.3
• /
• pp.41-48
• /
• 2006

In this paper, we propose a new active queue management (AQM) scheme by utilizing the predictability of the Internet traffic. The proposed scheme predicts future traffic input rate by using the auto-regressive (AR) time series model and determines the future congestion level by comparing the predicted input rate with the service rate. If the congestion is expected, the packet drop probability is dynamically adjusted to avoid the anticipated congestion level. Unlike the previous AQM schemes which use the queue length variation as the congestion measure, the proposed scheme uses the variation of the traffic input rate as the congestion measure. By predicting the network congestion level, the proposed scheme can adapt more rapidly to the changing network condition and stabilize the average queue length and its variation even if the traffic input level varies widely. Through ns-2 simulation study in varying network environments, we compare the performance among RED, Adaptive RED (ARED), REM, Predicted AQM (PAQM) and the proposed scheme in terms of average queue length and packet drop rate, and show that the proposed scheme is more adaptive to the varying network conditions and has shorter response time.