Search

International audience; This paper presents an optimization model for Home Energy Management Systems from an aggregator’s standpoint. The aggregator manages a set of resources such as PV, electrochemical batteries and thermal energy storage by means of electric water heaters. Resources are managed in order to participate in the day-ahead energy and local flexibility markets, also considering grid constraint support at the Point of Common Coupling. The resulting model is a Mixed-Integer Linear Programming problem in which the objective is to minimize day-ahead operation costs for the aggregator while complying with energy commitments in the day-ahead market and local flexibility requests. Three sources of uncertainty are considered: energy prices, PV production and load. Adjustable Robust Optimization is used to find a robust counterpart of the problem for including uncertainty. The results obtained show that using robust optimization allows strategic bidding to capture uncertainties while complying with obligations in the wholesale and local market. Data from a real-life energy community with 25 households is used to validate the proposed robust bidding methodology.

International audience; Energy forecasting models deployed in industrial applications face uncertainty w.r.t. data availability, due to network latency, equipment malfunctions or data-integrity attacks. In particular, the case when a subset of features that has been used for model training becomes unavailable when the model is used operationally, poses a major challenge to forecasting performance. In this work, we present a principled approach to introducing resilience against missing features in energy forecasting applications via robust optimization. Specifically, we formulate a robust regression model that is optimally resilient against missing features at test time, considering both point and probabilistic forecasting. We develop three solution methods for the proposed robust formulation, all leading to Linear Programming problems, with varying degrees of tractability and conservativeness. We provide an extensive empirical validation of the proposed methods in prevalent applications, namely, electricity price, load, wind production, and solar production, forecasting, and we further compare against well-established benchmark models and methods of dealing with missing features, i.e., imputation and retraining. Our results demonstrate that the proposed robust optimization approach outperforms imputationbased models and exhibits similar performance to retraining without the missing features, while also maintaining practicality. To the best of our knowledge, this is the first work that introduces resilience against missing features into energy forecasting.