Jianghua Ge, Jiwei Wen, Chuntao Zhang, Yaping Wang, Gang Ding
언어
영어(ENG)
URL
https://www.earticle.net/Article/A246184
※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.
원문정보
초록
영어
The power generation prediction problem can be seen as a time series prediction problem in nature. The traditional time series prediction methods based on regression analysis do not take account into the time accumulation effect existed in the time series due to their discrete input values. This limitation causes the low prediction accuracy of the time series prediction methods based on regression analysis. To solve this problem, a power generation time series prediction model based on the process neural network is proposed. The inputs of the proposed prediction model can be continuous time-varying functions. The time accumulation effect existed in the power generation time series can be expressed and computed by the integration operator of the process neural network. The proposed prediction model is trained and the efficiency of the proposed prediction model is tested by the month power generation data form January 2001 to April 2012, and the comparison experiment results indicate that the process neural network performs better than the auto regression analysis.
목차
Abstract 1. Introduction 2. Time Series Prediction Model based on Process Neural Network 2.1. The Process Neuron 2.2. Time Series Prediction Model 2.3. The Learning Algorithm 3. Application and Verification 4. Conclusions Acknowledgements References
보안공학연구지원센터(IJUNESST) [Science & Engineering Research Support Center, Republic of Korea(IJUNESST)]
설립연도
2006
분야
공학>컴퓨터학
소개
1. 보안공학에 대한 각종 조사 및 연구
2. 보안공학에 대한 응용기술 연구 및 발표
3. 보안공학에 관한 각종 학술 발표회 및 전시회 개최
4. 보안공학 기술의 상호 협조 및 정보교환
5. 보안공학에 관한 표준화 사업 및 규격의 제정
6. 보안공학에 관한 산학연 협동의 증진
7. 국제적 학술 교류 및 기술 협력
8. 보안공학에 관한 논문지 발간
9. 기타 본 회 목적 달성에 필요한 사업
간행물
간행물명
International Journal of u- and e- Service, Science and Technology
간기
격월간
pISSN
2005-4246
수록기간
2008~2016
십진분류
KDC 505DDC 605
이 권호 내 다른 논문 / International Journal of u- and e- Service, Science and Technology Vol.8 No.5