http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Talip Sari, Tolga (검색결과 1 건)
- 무료
- 기관 내 무료
- 유료
-
Energy-Efficient RL-Based Aerial Network Deployment Testbed for Disaster Areas
Ariman, Mehmet,Akkoc, Mertkan,Talip Sari, Tolga,Erol, Muhammed Rasit,Seçinti, Gökhan,Canberk, Berk 한국통신학회 2023 Journal of communications and networks Vol.25 No.1
Rapid deployment of wireless devices with 5G andbeyond enabled a connected world. However, an immediatedemand increase right after a disaster paralyzes network in-frastructure temporarily. The continuous flow of information iscrucial during disaster times to coordinate rescue operations andidentify the survivors. Communication infrastructures built for users of disaster areasshould satisfy rapid deployment, increased coverage, and avail-ability. Unmanned air vehicles (UAV) provide a potential solutionfor rapid deployment as they are not affected by traffic jamsand physical road damage during a disaster. In addition, ad-hocWiFi communication allows the generation of broadcast domainswithin a clear channel which eases one-to-many communications. Moreover, using reinforcement learning (RL) helps reduce thecomputational cost and increases the accuracy of the NP-hardproblem of aerial network deployment. To this end, a novel flying WiFi ad-hoc network managementmodel is proposed in this paper. The model utilizes deep-Q-learning to maintain quality-of-service (QoS), increase userequipment (UE) coverage, and optimize power efficiency. Fur-thermore, a testbed is deployed on Istanbul Technical Univer-sity (ITU) campus to train the developed model. Training resultsof the model using testbed accumulates over 90% packet deliveryratio as QoS, over 97% coverage for the users in flow tables, and0.28 KJ/Bit average power consumption.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
