Short-Term Load Forecasting Using AMI Data

Accurate short-term load forecasting is essential for the efficient operation of the power sector. Forecasting load at a fine granularity such as hourly loads of individual households is challenging due to higher volatility and inherent stochasticity. At the aggregate levels, such as monthly load at a grid, the uncertainties and fluctuations are averaged out; hence predicting load is more straightforward. This paper proposes a method called Forecasting using Matrix Factorization (textscfmf) for short-term load forecasting (textscstlf). textscfmf only utilizes historical data from consumers' smart meters to forecast future loads (does not use any non-calendar attributes, consumers' demographics or activity patterns information, etc.) and can be applied to any locality. A prominent feature of textscfmf is that it works at any level of user-specified granularity, both in the temporal (from a single hour to days) and spatial dimensions (a single household to groups of consumers). We empirically evaluate textscfmf on three benchmark datasets and demonstrate that it significantly outperforms the state-of-the-art methods in terms of load forecasting. The computational complexity of textscfmf is also substantially less than known methods for textscstlf such as long short-term memory neural networks, random forest, support vector machines, and regression trees.