http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
강수-일유출량 추정 LSTM 모형의 구축을 위한 자료 수집 방안
김동균,강석구,Kim, Dongkyun,Kang, Seokkoo 한국수자원학회 2021 한국수자원학회논문집 Vol.54 No.10
In this study, after developing an LSTM-based deep learning model for estimating daily runoff in the Soyang River Dam basin, the accuracy of the model for various combinations of model structure and input data was investigated. A model was built based on the database consisting of average daily precipitation, average daily temperature, average daily wind speed (input up to here), and daily average flow rate (output) during the first 12 years (1997.1.1-2008.12.31). The Nash-Sutcliffe Model Efficiency Coefficient (NSE) and RMSE were examined for validation using the flow discharge data of the later 12 years (2009.1.1-2020.12.31). The combination that showed the highest accuracy was the case in which all possible input data (12 years of daily precipitation, weather temperature, wind speed) were used on the LSTM model structure with 64 hidden units. The NSE and RMSE of the verification period were 0.862 and 76.8 m<sup>3</sup>/s, respectively. When the number of hidden units of LSTM exceeds 500, the performance degradation of the model due to overfitting begins to appear, and when the number of hidden units exceeds 1000, the overfitting problem becomes prominent. A model with very high performance (NSE=0.8~0.84) could be obtained when only 12 years of daily precipitation was used for model training. A model with reasonably high performance (NSE=0.63-0.85) when only one year of input data was used for model training. In particular, an accurate model (NSE=0.85) could be obtained if the one year of training data contains a wide magnitude of flow events such as extreme flow and droughts as well as normal events. If the training data includes both the normal and extreme flow rates, input data that is longer than 5 years did not significantly improve the model performance.
소프트웨어 정의 네트워크 통합 운영 및 관리 프레임워크
김동균(Dongkyun Kim),길준민(Joon-Min Gil) 한국디지털콘텐츠학회 2013 한국디지털콘텐츠학회논문지 Vol.14 No.4
An important research challenge about the traditional Internet environment is to enable open networking architecture on which end users are able to innovate the Internet based on the technologies of network programmability, virtualization, and federation. The SDN (Software Defined Network) technology that includes OpenFlow protocol specifications, is suggested as a major driver for the open networking architecture, and is closely coupled with the classical Internet (non-SDN). Therefore, it is very important to keep the integrated SDN and non-SDN network infrastructure reliable from the view point of network operators and engineers. Under this background, this paper proposes an operations and management framework for the combined software defined network environment across not only a single-domain network, but also multi-domain networks. The suggested framework is designed to allow SDN controllers and DvNOC systems to interact with each other to achieve sustainable end-to-end user-oriented SDN and non-SDN integrated network environment. Plus, the proposed scheme is designed to apply enhanced functionalities on DvNOC to support four major network failure scenarios over the combined network infrastructure, mainly derived from SDN controllers, SDN devices, and the connected network paths.
프로토콜 제어 및 데이터부분시험을 위한 통합시험항목생성
김동균(Dongkyun Kim),최양희(Yanghee Choi) 한국정보과학회 1995 한국정보과학회 학술발표논문집 Vol.22 No.2B
통신프로토콜이 복잡해짐에 따라 이를 검증하기 위한 여러 방법들이 출현하였다. 이러한 방법들로는 프로토콜을 기술하고 기술된 내용에 논리적인 오류가 발생하였는가의 여부를 조사하는 Validation 검사와, 프로토콜의 구현이 프로토콜 규격과 일치하는가의 여부를 검사하는 적합성시험(Conformance Testing)이 존재한다. 적합성시험은 블랙박스 시험으로 수행되며 지금까지 프로토콜의 제어부분에 대한 연구가 많이 진행되었다. 지금까지 제시된 데이터부분을 고려한 적합성시험방법들은 일반적으로 단순히 제어부분과 데이터부분을 구별하여 독립적으로 시험항목을 생성하고 있다. 본 논문에서는 하나의 시험항목으로 통합시험하는 새로운 방법을 제시한다.