*Article* **Machine Learning Techniques for Improving Self-Consumption in Renewable Energy Communities**

#### **Zacharie De Grève 1,\*, Jérémie Bottieau 1, David Vangulick 2, Aurélien Wautier 1, Pierre-David Dapoz 1, Adriano Arrigo 1, Jean-François Toubeau 1 and François Vallée**


Received: 15 July 2020; Accepted: 14 September 2020; Published: 18 September 2020

**Abstract:** Renewable Energy Communities consist in an emerging decentralized market mechanism which allows local energy exchanges between end-users, bypassing the traditional wholesale/retail market structure. In that configuration, local consumers and prosumers gather in communities and can either cooperate or compete towards a common objective, such as the minimization of the electricity costs and/or the minimization of greenhouse gas emissions for instance. This paper proposes data analytics modules which aim at helping the community members to schedule the usage of their resources (generation and consumption) in order to minimize their electricity bill. A day-ahead local wind power forecasting algorithm, which relies on state-of-the-art Machine Learning techniques currently used in worldwide forecasting contests, is in that way proposed. We develop furthermore an original method to improve the performance of neural network forecasting models in presence of abnormal wind power data. A technique for computing representative profiles of the community members electricity consumption is also presented. The proposed techniques are tested and deployed operationally on a pilot Renewable Energy Community established on an Medium Voltage network in Belgium, involving 2.25 MW of wind and 18 Small and Medium Enterprises who had the possibility to freely access the results of the developed data modules by connecting to a dedicated web platform. We first show that our method for dealing with abnormal wind power data improves the forecasting accuracy by 10% in terms of Root Mean Square Error. The impact of the developed data modules on the consumption behaviour of the community members is then quantified, by analyzing the evolution of their monthly self-consumption and self-sufficiency during the pilot. No significant changes in the members behaviour, in relation with the information provided by the models, were observed in the recorded data. The pilot was however perturbed by the COVID-19 crisis which had a significant impact on the economic activity of the involved companies. We conclude by providing recommendations for the future set up of similar communities.

**Keywords:** energy communities; machine learning; forecasting; abnormal data; wind power; outliers; electricity consumption representative profiles; self-consumption
