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 : Caihong Kai (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Yuanguang Wu,Lusheng Wang,Caihong Kai,Min Peng 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.12
Task offloading in vehicular networks is hot topic in the development of autonomous driving. In these scenarios, due to the role of vehicles and pedestrians, task characteristics are changing constantly. The classical deep learning algorithm always uses a pre-trained neural network to optimize task offloading, which leads to system performance degradation. Therefore, this paper proposes a neural network fine-tuning task offloading algorithm, combining with location prediction for pedestrians and vehicles by the Payne model of fluid dynamics and the car-following model, respectively. After the locations are predicted, characteristics of tasks can be obtained and the neural network will be fine-tuned. Finally, the proposed algorithm continuously predicts task characteristics and fine-tunes a neural network to maintain high system performance and meet low delay requirements. From the simulation results, compared with other algorithms, the proposed algorithm still guarantees a lower task offloading delay, especially when congestion occurs.
-
A Mass-Processing Simulation Framework for Resource Management in Dense 5G-IoT Scenarios
( Lusheng Wang ),( Kun Chang ),( Xiumin Wang ),( Zhen Wei ),( Qingxin Hu ),( Caihong Kai ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.9
Because of the increment in network scale and test expenditure, simulators gradually become main tools for research on key problems of wireless networking, such as radio resource management (RRM) techniques. However, existing simulators are generally event-driven, causing unacceptably large simulation time owing to the tremendous number of events handled during a simulation. In this article, a mass-processing framework for RRM simulations is proposed for the scenarios with a massive amount of terminals of Internet of Things accessing 5G communication systems, which divides the time axis into RRM periods and each period into a number of mini-slots. Transmissions within the coverage of each access point are arranged into mini-slots based on the simulated RRM schemes, and mini-slots are almost fully occupied in dense scenarios. Because the sizes of matrices during this process are only decided by the fixed number of mini-slots in a period, the time expended for performance calculation is not affected by the number of terminals or packets. Therefore, by avoiding the event-driven process, the proposal can simulate dense scenarios in a quite limited time. By comparing with a classical event-driven simulator, NS2, we show the significant merits of our proposal on low time and memory costs.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
