Photovoltaic (PV) power prediction, as a necessary technical requirement of PV plants, closely relates to the accuracy and rationality of power grid dispatch. If the output power of PV plants can be further enhanced by forecasting, the risk of grid-connected will be greatly reduced, and the safety and stability of power grid will be increased. Therefore, we propose a novel short-term forecasting model of output power based on the MEA-BP, which is optimized by Mind Evolutionary Algorithm (MEA) and Back-Propagation (BP) neural network. We focus on the actual operation of 100MW large grid-integrated PV station, which takes the important meteorological factors and historical generation data of PV station. In our research, the prediction problem includes four units according to different seasons, different data, and the output of PV station respectively. The experimental results show the prediction accuracy in different prediction units. The proposed MEA-BP model efficiently reduces the prediction errors compared with the traditional BP model.
목차
Abstract 1. Introduction 2. MEA-BP Neural Network 2.1. An overview of Mind Evolutionary Algorithm (MEA) 2.2. The Process of the MEA 2.3. The Design of the MEABP Network 3. The Design of Prediction Model based on the MEABP Network 3.1. The Network Structure of MEA-BP 3.2. Training and Evaluation of MEA-BP Network 4. Example Analysis 5. Conclusions References
키워드
Short-term forecastMEA-BPneural networkMW-level PV station
저자
Renjie Song [ School of Information Science and Engineering, Northeast Dianli University JiLin, JiLin, China ]
Fusheng Liu [ School of Information Science and Engineering, Northeast Dianli University JiLin, JiLin, China ]
Zijian Jing [ State Grid Jilin Electric Power Co., Ltd. Jilin power company, Jilin 132012, China ]
Dajun Lv [ Beijing Guo Dian Zhi Shen Control Technology Co.Ltd Beijing China ]
보안공학연구지원센터(IJAST) [Science & Engineering Research Support Center, Republic of Korea(IJAST)]
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 Advanced Science and Technology
간기
월간
pISSN
2005-4238
수록기간
2008~2016
십진분류
KDC 505DDC 605
이 권호 내 다른 논문 / International Journal of Advanced Science and Technology Vol.94