Abstract
In order to reduce the cost of data transmission, the meter data management system (MDMS) of the power operator usually delays time to obtain the power generation information of a solar photovoltaic (PV) power generation system. Although this approach solves the problem of data transmission cost, it brings more challenges to the solar PV power generation forecast. Because power operators usually need real-time solar PV power generation as a basis for the power dispatch, but considering the cost of communication, they cannot always provide corresponding historical power generation data in real time. In this study, an intelligent solar PV power generation forecasting mechanism combined with weather information is designed to cope with the issue of the absence of real-time power generation data. Firstly, the Pearson correlation coefficient analysis is used to find major factors with a high correlation in relation to solar PV power generation to reduce the computational burden of data fitting via a deep neural network (DNN). Then, the data preprocessing, including the standardization and the anti-standardization, is adopted for data-fitting or real-time solar PV power generation data to take as the input data of a long short-term memory neural network (LSTM). The salient features of the proposed DNN-LSTM model are: (1) only the information of present solar PV power generation is required to forecast the one at the next instant, and (2) an on-line learning mechanism is helpful to adjust the trained model to adapt different solar power plant or environmental conditions. In addition, the effectiveness of the trained model is verified by six actual solar power plants in Taiwan, and the superiority of the proposed DNN-LSTM model is compared with other forecasting models. Experimental verifications show that the proposed forecasting model can achieve a high accuracy of over 97%.