In the context of the smart grid, scheduling residential energy storage device is necessary to optimize technical and market integration of distributed energy resources (DERs), especially the ones based on renewable energy. The first step to achieve proper scheduling of the storage devices is electricity consumption forecasting at individual household level. This paper compares the forecasting ability of Artificial Neural Network (ANN) and AutoRegressive Integrated Moving Average (ARIMA) model. The benefit of proper storage scheduling is demonstrated via a use-case. The work is a part of a project focused on photovoltaic generation with integrated energy storage at household level. The methods under study attempt to capture the daily electricity consumption profile of an individual household.
|Title of host publication||Proceedings 49th International Universities' Power Engineering Conference (UPEC) 2014, 2-5 September 2014, Cluj-Napoca, Romania|
|Publisher||Institute of Electrical and Electronics Engineers|
|Publication status||Published - 2014|
Ahmed, K. M. U., Ampatzis, M., Nguyen, P. H., & Kling, W. L. (2014). Application of time-series and artificial neural network models in short term load forecasting for scheduling of storage devices. In Proceedings 49th International Universities' Power Engineering Conference (UPEC) 2014, 2-5 September 2014, Cluj-Napoca, Romania (pp. 1-6). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/UPEC.2014.6934761