Energy load forecasting in big data context

Smart grid is now making a significant impact on energy management. In fact, adding smart meters to the power grid allow a better system monitoring and control. In addition, it has also allowed a variety of data to be captured. Handling consumers needs is beneficial for a wise energy production and consumption. However, a challenging task in energy management concerns estimating the future energy demand of consumers, especially when consumers change their behavior. A key element to tackle this issue, is by analyzing smart grid data, and discovering hidden patterns and factors that can effectively be used to predict energy consumption. In this paper, we are interested in the effect of external variables on energy consumption. We first present the state of art of energy load forecasting approaches, also highlight the challenges associated with big energy data. Then we provide a comparison of machine learning approaches for energy load production in a big data context. Experimental results show the contribution of external variables on the model's accuracy and interpretability.