Photovoltaic power generation forecasting is an important topic in field of sustainable power system design, energy conversion management and smart grid construction. Difficulties arise while the generated PV power is usually unstable due to the variability of solar irradiance, temperature and other meteorological factors. In this study, a hybrid ensemble deep learning framework is proposed to forecast short-term photovoltaic power generation in a time series manner. Two LSTM neural networks are employed working on temperature and power outputs forecasting respectively. The forecasting results are flattened and combined with a fully connected layer to enhance the forecasting accuracy. Moreover, we adopted the attention mechanism for the two LSTM neural networks to adaptively focus on input features that are more significant in forecasting. Comprehensive experiments are conducted with recently collected real-world photovoltaic power generation datasets. Three error metrics were adopted to compare the forecasting results produced by attention LSTM model with state-of-art methods, including the persistent model, the auto-regressive integrated moving average model with exogenous variable (ARIMAX), multi-layer perceptron (MLP) and the traditional LSTM model in all four seasons and various forecasting horizons to show the effectiveness and robustness of the proposed method.

Electric power consumption short-term forecasting for individual households is an important and challenging topic in the fields of AI-enhanced energy saving, smart grid planning, sustainable energy usage and electricity market bidding system design. Due to the variability of each household’s personalized activity, difficulties exist for traditional methods, such as auto-regressive moving average models, machine learning methods and non-deep neural networks, to provide accurate prediction for single household electric power consumption. Recent works show that the long short term memory (LSTM) neural network outperforms most of those traditional methods for power consumption forecasting problems. Nevertheless, two research gaps remain as unsolved problems in the literature. First, the prediction accuracy is still not reaching the practical level for real-world industrial applications. Second, most existing works only work on the one-step forecasting problem; the forecasting time is too short for practical usage. In this study, a hybrid deep learning neural network framework that combines convolutional neural network (CNN) with LSTM is proposed to further improve the prediction accuracy. The original short-term forecasting strategy is extended to a multi-step forecasting strategy to introduce more response time for electricity market bidding. Five real-world household power consumption datasets are studied, the proposed hybrid deep learning neural network outperforms most of the existing approaches, including auto-regressive integrated moving average (ARIMA) model, persistent model, support vector regression (SVR) and LSTM alone. In addition, we show a k-step power consumption forecasting strategy to promote the proposed framework for real-world application usage.