http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
건물적용 태양광발전시스템의 유지관리를 위한 인공신경망 기반 최대출력점 예측 연구
이효문(Lee Hyomun),김동수(Kim Dongsu),윤종호(Yoon Jongho) 한국태양에너지학회 2021 한국태양에너지학회 논문집 Vol.41 No.5
To achieve the greatest performance, photovoltaic (PV) systems need to be continuously monitored for fault detection and diagnosis, which could affect their performance under operational conditions. Various fault detection and diagnosis methods have been developed to improve these technologies. For example, the “Voltage and Current Measurement Method” based on the One-Diode model has been widely adopted in many case studies to predict a maximum power point (i.e., power, current, and voltage) and then detect any issues that occur under harsh outdoor conditions. Although the One-Diode model has demonstrated accurate performance for fault detection and diagnosis, the accuracy has typically been limited to crystalline PV modules. To overcome this limitation, many fault diagnosis methods have been proposed, and machine-learning fault detection and diagnosis methods are effective alternatives because of the nonlinear output features and varying operating conditions of PV arrays. Therefore, this study presents the prediction model of maximum power point (MPP) using artificial neural network (ANN) algorithms. The prediction model of MPP was generated through an optimization analysis. The MPP was validated by using measured data obtained from a building attached to a PV (BAPV) system in Korea. The results of the optimization study showed the highest predictive accuracy when the structure of the ANN model was trained and learned with one hidden layer, 20 neurons per hidden layer, a sigmoid function, and an 0.01 learning rate. The coefficient of variation of RMS error (CvRMSE) between the predicted value and the labelled value was 3.14%. The prediction model for MPP was verified by using the measured data. The analysis of the measured and predicted values resulted in CvRMSE values of 11.66%, 11.70%, and 18.01% for power, current, and voltage, respectively.
이효문(Lee Hyomun),배상순(Bae SangSoon),최민주(Choi Minjoo),김동수(Kim Dongsu),윤종호(Yoon Jongho) 한국태양에너지학회 2022 한국태양에너지학회 논문집 Vol.42 No.5
Photovoltaic (PV) systems are commonly used as on-site electric power generators for ZEBs in the Republic of Korea. To enhance the performance of PV systems, considering efficient installation conditions, such as the optimal azimuth and tilt angles, is critical. Under domestic PV application guidelines, the azimuth of installation for building-applied PV systems is stipulated within a maximum of ±90° based on the south-facing direction. In general, the north-facing direction is known as a weak position for PV systems. However, several studies have shown that the north-facing direction can be a good option for building PV installations, typically when the installation areas are limited within a building site. Even if the PV panel faces north, the system can operate effectively with proper performance when installed at a suitable inclination angle. In existing studies, system behavior has been verified based on simulation-based analysis, but actual operational data analysis remains insufficient. This study aims to evaluate the feasibility of north-facing PV systems based on a performance evaluation of the measured data of a roof PV system. The roof PV system analyzed in this study was composed of modules, module-level power electronics (MLPE), and one inverter. The PV modules and MLPEs were installed on both the southern (SIR) and northern (NIR) inclined roofs. Based on the annual cumulative DC power, the energy yields of the MLPE connected to modules of the SIR and NIR are 1,445.0 and 1,068.7 ㎾h/㎾p, respectively. Our study found that the ratio of the performance of MLPE on the NIR to MLPE on the SIR was 74.0%. This ratio was similar to the energy yield of the PV system on the south vertical plane as compared to that on the south slope plane. The analyzed results revealed that an acceptable performance of the PV system installed on a northern slope at a suitable inclination angle could be expected as compared with other PV installations such as the southern vertical.