AUTHOR=Liu Yongjiu , Li Li , Zhou Shenglin TITLE=Ensemble Forecasting Frame Based on Deep Learning and Multi-Objective Optimization for Planning Solar Energy Management: A Case Study JOURNAL=Frontiers in Energy Research VOLUME=Volume 9 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.764635 DOI=10.3389/fenrg.2021.764635 ISSN=2296-598X ABSTRACT=Several prediction models have been adopted to predict photovoltaic power, which is abnormal and non-linear. Nonetheless, the validity of data preprocessing and ensemble learning strategies is always neglected, which leads to low forecasting precision and low stability of photovoltaic power. To overcome these drawbacks, an ensemble forecasting frame based on the data pretreatment technology, multi-objective optimization algorithm, statistical method, and deep learning methods is developed. To verify the validity of the system, datasets of 15-minute photovoltaic power output obtained from different time periods in Belgium were employed. The forecasting results prove that the frame positively surpasses all the reference models in terms of prediction accuracy and stabilization. For one-, two-, and three-step predictions, the MAPE values obtained from the proposed frame were less than 2%, 3%, and 5%, respectively. Therefore, the proposed frame is highly serviceable in elevating forecasting accuracy and can be used as an efficient instrument for intelligent grid programming.