• Journal of the Korean Statistical Society
• /
• 제26권3호
• /
• pp.355-363
• /
• 1997

In queueing theory, polling systems have been widely studied as a way of serving several stations in cyclic order. In this paper we consider Markov-modulated Poisson process which is useful for approximating a superposition of heterogeneous arrivals. We derive the mean waiting time of each station in a polling system where the arrival process is modeled by a Markov-modulated Poisson process.

• 대한임베디드공학회논문지
• /
• 제14권2호
• /
• pp.63-69
• /
• 2019

Recently, ultra-low latency flash storage devices such as Z-SSD and Optane SSD were introduced with the significant technological improvement in the storage devices which provide much faster response time than today's other NVMe SSDs. With such ultra-low latency, $10{\mu}s$, storage devices the cost of context switch could be an overhead during interrupt-driven I/O completion process. As an interrupt-driven I/O completion process could bring an interrupt handling overhead, polling or hybrid-polling for the I/O completion is known to perform better. In this paper, we analyze tail latency problem in a polling process caused by process scheduling in data center environment where multiple applications run simultaneously under one system and we introduce our adaptive polling selection technique which dynamically selects efficient processing method between two techniques according to the system's conditions.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.982-983
• /
• 2013

이 논문에서는 XG-PON의 동적 polling 방법을 소개하고 그 성능을 평가한 결과를 소개한다. 컴퓨터 시뮬레이션을 통하여 기존방법과 평균시지연 및 시지연분산을 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1393-1405
• /
• 2017

It is well known that duty-cycling control by dynamically adjusting the polling interval according to the traffic loads can effectively achieve power saving in wireless sensor networks. Thus, there has been a significant research effort in developing polling interval adaptation schemes. Especially, Dynamic Low Power Listening (DLPL) scheme is one of the most widely adopted open-looping polling interval adaptation techniques in wireless sensor networks. In DLPL scheme, if consecutive idle (busy) samplings reach a given fixed threshold, the polling interval is increased (decreased). However, due to the trial-and-error based approach, it may significantly deteriorate the system performance depending on given threshold parameters. In this paper, we propose a novel DLPL scheme, called SDL (Sequential hypothesis testing based Dynamic LPL), which employs sequential hypothesis testing to decide whether to change the polling interval conforming to various traffic conditions. Simulation results show that SDL achieves substantial power saving over state-of-the-art DLPL schemes.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2198-2202
• /
• 2003

The data transmission of MVB(Multifunction Vehicle Bus) of TCN(Train Network Communication) is divided into the periodic transmission phase and the sporadic transmission phase. TCN standard defines the event-polling method for the message transfer in the sporadic phase. However, since the event-polling method does not use pre-scheduling to the priority of the messages to be transmitted, it is inefficient for the real-time systems. To schedule message transmission, a master node should know the priority of message to be transmitted by a slave node prior to the scheduling the sporadic phase, but the existing TCN standard does not support any protocol for this. This paper proposes the slave frame bit-stuffing algorithm, with which a master node gets the necessary information for transmission scheduling and includes the simulation results of the event-polling method and the proposed algorithm.

• 대한산업공학회지
• /
• 제32권1호
• /
• pp.1-8
• /
• 2006

A modified PCF(Point Coordination Function) protocol with the optimal polling sequence is defined in detail and shown to improve the efficiency of the conventional PCF protocol in IEEE 802.11 wireless LAN standard. The problem for the optimal polling sequence is formulated as TSP(Travelling Salesman Problem) with the distance values of 1's or 0's. Numerical examples show that the optimal polling sequence increases the capacity of the real-time service such as VoIP(Voice over Internet Protocol).

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.1013-1017
• /
• 2005

This paper proposes an effective algorithm, P-DCF(Polling DCF) to satisfy real-time requirements in the industrial environments, based on 802.11 DCF protocols. Theoretical analysis and actual experiments are carried out, which shows that the proposed P-DCF brings several benefits: 1) it reduces the time delay for frame transmission 2)it guarantees bounded upper limit of maximum transmission delay 3) it maintains fairness

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권10호
• /
• pp.720-726
• /
• 2004

The data transmission over MVB(Multifunction Vehicle Bus) of TCN(Train Communication Network) is divided into the periodic transmission phase and the sporadic transmission phase. TCN standard recommends the event-polling method as the message transfer in the sporadic phase. However, since the event-polling method does not use pre-scheduling to the priority of the messages, it is inefficient for the real-time systems. To schedule message transmission, a master node should know the priority of message to be transmitted by a slave node prior to the sporadic phase, but the existing TCN standard does not support any protocol for this. This paper proposes the slave frame bit-stuffing algorithm, with which a master node gets the necessary information for scheduling and includes the simulation results of the event-polling method and the proposed algorithm.

• 대한산업공학회지
• /
• 제33권2호
• /
• pp.237-245
• /
• 2007

In this paper, a modified PCF (Point Coordination Function) MAC (Medium Access Control) Protocol is proposed to support the multiple direct link communication between STAs (STAtions) in infrastructure mode IEEE 802.11 wireless LANs. By the proposed MAC protocol, the direct link communication between STAs, which are located within the communication range of each other, is allowed without the use of AP (Access Point) as a relay. Moreover, when multiple direct data communication between STAs can be simultaneously performed with a sufficiently small interference, multiple simultaneous direct link communication is allowed for the efficient use of radio bandwidth. AP polls STAs to grant the transmission opportunities using the direct link communication by transmitting the polling frames to STAs. An efficient polling method for granting the transmission opportunities to STAs is proposed to reduce the number of the polling frame transmissions and enhance the PCF MAC performance.

• 한국컴퓨터정보학회논문지
• /
• 제5권4호
• /
• pp.120-125
• /
• 2000

기존의 인터넷 망 관리에 사용되는 SNMP(Simple Network Management Protocol)는 망 관리 정보 수집을 위한 폴링과 이에 대한 응답 트래픽으로 관리자 시스템(Management System)이 관리하는 피관리 시스템(Agent System)이 많아지면 망의 과부하를 가져올 수 있다. 본 논문에서는 기존의 SNMP에서 사용하는 폴링 방법을 개선하여 피관리 시스템이 많은 경우에 망의 과부하를 줄일 수 있는 그룹 폴링 방법을 제안하였다. 제안한 방법은 피관리 시스템들을 그룹으로 나누어 정보를 수집하는 방식으로, 기존의 방식에 비해 응답 지연시간과 통신 부하가 줄어서 피관리 시스템의 수가 많은 경우나 폴링 횟수가 많은 경우, 제안된 그룹 폴링 방법을 이용하는 것이 효율적이었다.