In the recent years, several short-term forecasting models of household electricity demand have been proposed in the literature. This is partly due to emerging smart-grid applications, which require these kinds of forecasts to manage systems such as smart homes, prosumer aggregations, etc., and partly thanks to the availability of data from smart meters, which enable the development of such models. Since most models are academically developed, they often do not address challenges related to their implementation in a real-world environment. In the latter case, several issues arise, related to data quality and availability, which affect the operational performance and robustness of a forecasting system. In this paper, we design a hierarchical forecasting framework based on a total of 5 probabilistic models of varying complexity, after analyzing the respective performance and advantages of the models with an offline dataset. This multi-layered framework is necessary to address the various problematic situations occurring in practice and abide by the requirements for a real-world deployment. The forecasting system is deployed in a real-world case and evaluated here on data from 20 households. Field data, comprising forecasts and measurements, are analyzed for each household. A detailed comparison is drawn between the online and offline performances. Since a notable degradation is observed in the operational environment, we discuss at length the reasons for such an effect. We determine that the exact settings of the training and test periods are marginally responsible, but that the main cause is the intrinsic evolution of the demand time series, which hinders the forecasting performance. This evolution is due to unknown household characteristics that need to be monitored to provide more adaptable models.

International audienceThis paper presents the objectives and an overview of the results obtained in the frame of the ANEMOS project on short-term wind power forecasting. The aim of the project is to develop accurate models that substantially outperform current state-of-the-art methods, for onshore and offshore wind power forecasting, exploiting both statistical and physical modeling approaches. The project focus on prediction horizons up to 48 hours ahead and investigates predictability of wind for higher horizons up to 7 days ahead useful i.e. for maintenance scheduling. Emphasis is given on the integration of high-resolution meteorological forecasts. Specific modules are also developed for on-line uncertainty and prediction risk estimation. An integrated software platform, 'ANEMOS', is developed to host the various models. This system is installed by several end-users for on-line operation at onshore and offshore wind farms for prediction at a local, regional and national scale. The applications include different terrain types and wind climates, on- and offshore cases, and interconnected or island grids

This article addresses the developments ongoing in SENSIBLE, an H2020 funded project focused on energy storage and energy management, which demonstration occurs in Évora-Portugal, Nottingham-UK and Nuremberg-Germany. Currently presented work focus the concepts and developments necessary in order to make possible that residential clients can participate in a market environment with their electrical flexibility, also considering Distribution System Operator (DSO) needs when gird is under stress caused by any technical constraint. Moreover than the concept behind it is necessary to consider several developments: i) a low layer where residential assets will live in customers houses; ii) a high-level layers where market tools and DSO management tools will live; iii) an intermediate layer which bridge the gap between the low layer and high layer. These developments are a result of the ongoing works under one of SENSIBLE use cases which demonstrations occurs in a small village in Évora district in Portugal.