[논문]Performance Enhancement of CSMA/CA MAC Protocol Based on Reinforcement Learning

Kim, Tae-Wook; Hwang, Gyung-Ho

doi:10.6109/jicce.2021.19.1.1

Performance Enhancement of CSMA/CA MAC Protocol Based on Reinforcement Learning 원문보기

Journal of information and communication convergence engineering, v.19 no.1, 2021년, pp.1 - 7

Kim, Tae-Wook (Department of Computer Engineering, Hanbat National University) , Hwang, Gyung-Ho (Department of Computer Engineering, Hanbat National University)

Abstract ▼ AI-Helper

Reinforcement learning is an area of machine learning that studies how an intelligent agent takes actions in a given environment to maximize the cumulative reward. In this paper, we propose a new MAC protocol based on the Q-learning technique of reinforcement learning to improve the performance of the IEEE 802.11 wireless LAN CSMA/CA MAC protocol. Furthermore, the operation of each access point (AP) and station is proposed. The AP adjusts the value of the contention window (CW), which is the range for determining the backoff number of the station, according to the wireless traffic load. The station improves the performance by selecting an optimal backoff number with the lowest packet collision rate and the highest transmission success rate through Q-learning within the CW value transmitted from the AP. The result of the performance evaluation through computer simulations showed that the proposed scheme has a higher throughput than that of the existing CSMA/CA scheme.

주제어

표/그림 (9)

그림 Fig. 1. Illustration of the IEEE 802.11 wireless LAN CSMA/CA MAC protocol.
그림 Fig. 2. Overview of reinforcement learning.
그림 Fig. 3. Algorithm for AP to adjust CW
그림 Fig. 4. Algorithm for a station to determine its own backoff number using reinforcement learning.
그림 Fig. 5. Throughput comparison of proposed method and standard scheme when the initial CW is set to 15 and 31 respectively.
그림 Fig. 6. Throughput performance for different values of TH_F.
표 Table 1. Simulation parameters
그림 Fig. 7. Throughput performance for different values of TH_F when the number of stations was 61 to 70.
그림 Fig. 8. Throughput performance for different values of P_C.

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

A simulation was performed using MATLAB to verify the performance of the proposed CSMA/CA protocol using reinforcement learning. It was assumed that the station always contained packets that needed to be transmitted.
In this paper, we propose an algorithm that uses the Q learning technique of reinforcement learning to select a backoff number within the CW provided by the access point (AP). Through reinforcement learning, the stations can continue to select a backoff number with a high transmission success rate.
In this paper, we proposed an algorithm based on reinforcement learning to improve the performance of the IEEE 802.11 wireless LAN CSMA/CA MAC protocol. The AP continuously monitors the status of packets transmitted from the stations and informs the stations of the changes in CW according to the successive number of transmission successes or failures.
In the existing CSMA/CA method, the CW value is doubled each time there is a collision to determine the optimal CW value. In this study, the AP broadcasts the CW value to the stations through a broadcasting beacon frame and each station chooses a backoff number to reduce collisions.
for each AP and station. The AP adjusts the CW value according to the channel condition, and the station finds a backoff number that can maximize the transmission success rate through a Q-learning technique within the received CW value.
4. The station randomly selects a backoff number in the range from 1 to the CW value, which is received from the AP, and generates a Q-value array of size CW. When the station receives a new CW value from the AP, all Q-values are initialized to 0.

이론/모형

11 wireless LAN CSMA/CA MAC protocol, all stations change the CW value according to the failure or success of the packet transmis- sion. However, in the proposed method, all stations use the same CW and select one backoff number from 1 to the CW value according to the Q-learning algorithm. To determine the appropriate CW value in the given traffic conditions, the AP changes the CW value according to the number of consecutive successes or collisions of the transmitted packets.
The AP continuously monitors the status of packets transmitted from the stations and informs the stations of the changes in CW according to the successive number of transmission successes or failures. The station selects a backoff number with the highest packet transmission success rate within a given CW using the Q-learning technique. From the simulation results, it can be inferred that the throughput of the proposed method is higher than that of the existing CSMA/CA method.

참고문헌 (8)

"IEEE Standard for Information technology-Telecommunications and information exchange between systems Local and metropolitan area networks-Specific requirements- Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications," in IEEE Std 802.11-2016, Dec. 2016. DOI: 10.1109/IEEESTD.2016.7786995.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, A Bradford Book, 2018. DOI: 10.5555/3312046.
H. V. Hasselt, A. Guez, and D. Silver, "Deep reinforcement learning with double Q-learning," in Proceedings of AAAI Conference on Artificial Intelligence, pp. 2094-2100, 2016. DOI: 10.5555/3016100.3016191.
S. Galzarano, A. Liotta, and G. Fortino, "QL-MAC: A Q-learning based MAC for wireless sensor networks," in Proceedings of International Conference on Algorithms and Architectures for Parallel Processing, pp. 267-275, 2013. DOI: 10.1007/978-3-319-03889-6_31.

상세보기
Y. Chu, P. D. Mitchell, and D. Grace, "ALOHA and Q-learning based medium access control for wireless sensor networks," in Proceedings of International Symposium on Wireless Communication Systems (ISWCS), pp. 511-515, 2012. DOI: 10.1109/ISWCS.2012.6328420.
M. Loganathan, T. Sabapathy, and M. Elshaikh, "Reinforcement learning based anti-collision algorithm for RFID systems," International Journal of Computing, pp. 155-168, 2019. DOI: 10.47839/ijc.18.2.1414.
S. Dhakal and S. Shin, "Precise-optimal frame length based collision reduction schemes for frame slotted Aloha RFID systems," KSII Transactions on Internet and Information Systems, vol. 8, no. 1, pp. 165-182, 2014. DOI: 10.3837/tiis.2014.01.010.

원문보기 상세보기
T. Ho and K. Chen, "Performance analysis of IEEE 802.11 CSMA/CA medium access control protocol," in Proceedings of PIMRC'96 - 7th International Symposium on Personal, Indoor, and Mobile Communications, pp. 407-411, 1996. DOI: 10.1109/PIMRC.1996.567426.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증