研究目的
To design an optimized ANN-MPPT technique based on a large experimental training data to avoid the system from having a high training error and to accurately track the optimal maximum power point under varying weather conditions.
研究成果
The proposed ANN-MPPT method demonstrates superior performance in tracking the optimal maximum power point with less oscillation and faster response time compared to the P&O-MPPT method. It effectively avoids the drift problem and achieves higher output power generation under varying weather conditions.
研究不足
The study is limited by the dependency on accurate training data for the ANN model and the specific conditions under which the PV system operates. The performance of the ANN-MPPT method may vary under different environmental conditions not covered in the training data.
1：Experimental Design and Method Selection:
The study employs an ANN technique for MPPT in PV systems, utilizing large experimental training data collected over one year. The methodology includes the design of an ANN model with irradiation and temperature as inputs and the available power at MPP as the output.
2：Sample Selection and Data Sources:
Data are collected from experimental tests of a PV system installed at Brunel University, London, UK, including irradiation and temperature measurements.
3：List of Experimental Equipment and Materials:
The PV system consists of a PV array, DC-DC boost converter, MPPT micro-controller, and a load. The PV array includes five PV modules connected in series.
4：Experimental Procedures and Operational Workflow:
The ANN model is trained, tested, and validated using the collected data. The performance of the ANN-MPPT method is compared with the P&O-MPPT method under simulated varying weather conditions.
5：Data Analysis Methods:
The performance is evaluated based on tracking time, oscillation around the MPP, and output power generation.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
