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

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 2.25MW 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.

[1]  Choong Seon Hong,et al.  Day-ahead Energy Sharing Schedule for the P2P Prosumer Community Using LSTM and Swarm Intelligence , 2020, 2020 International Conference on Information Networking (ICOIN).

[2]  Thorsten Staake,et al.  Explaining and predicting annual electricity demand of enterprises – a case study from Switzerland , 2018, Energy Inform..

[3]  Jean-François Toubeau,et al.  Recalibration of recurrent neural networks for short-term wind power forecasting , 2021 .

[4]  Juan M. Morales,et al.  Real-Time Demand Response Model , 2010, IEEE Transactions on Smart Grid.

[5]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[6]  Nadia Oudjane,et al.  Analysis and Implementation of an Hourly Billing Mechanism for Demand Response Management , 2017, IEEE Transactions on Smart Grid.

[7]  Chris Eliasmith,et al.  Hyperopt: a Python library for model selection and hyperparameter optimization , 2015 .

[8]  Pierre Pinson,et al.  Impact of Public Aggregate Wind Forecasts on Electricity Market Outcomes , 2017, IEEE Transactions on Sustainable Energy.

[9]  Laurine Duchesne,et al.  Sensitivity Analysis of a Local Market Model for Community Microgrids , 2019, 2019 IEEE Milan PowerTech.

[10]  Thomas Morstyn,et al.  Multiclass Energy Management for Peer-to-Peer Energy Trading Driven by Prosumer Preferences , 2019, IEEE Transactions on Power Systems.

[11]  Ying Wah Teh,et al.  Time-series clustering - A decade review , 2015, Inf. Syst..

[12]  Benjamin Sovacool,et al.  Electricity market design for the prosumer era , 2016, Nature Energy.

[13]  Tarek AlSkaif,et al.  Smart charging of community storage units using Markov chains , 2017, 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe).

[14]  Jean-François Toubeau,et al.  Deep Learning-Based Multivariate Probabilistic Forecasting for Short-Term Scheduling in Power Markets , 2019, IEEE Transactions on Power Systems.

[15]  Daniel Pérez Palomar,et al.  Demand-Side Management via Distributed Energy Generation and Storage Optimization , 2013, IEEE Transactions on Smart Grid.

[16]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[17]  Jean-François Toubeau,et al.  A New Cooperative Framework for a Fair and Cost-Optimal Allocation of Resources within a Low Voltage Electricity Community , 2020, ArXiv.

[18]  Damien Ernst,et al.  E-CLOUD, the open microgrid in existing network infrastructure , 2017 .

[19]  Andreas Ehrenmann,et al.  Unintended consequences: The snowball effect of energy communities , 2020 .

[20]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[23]  R. Ramakumar,et al.  A framework for intelligent control of SIRES for rural communities , 2017, 2017 IEEE Power & Energy Society General Meeting.

[24]  P. Pinson,et al.  Energy Collectives: A Community and Fairness Based Approach to Future Electricity Markets , 2019, IEEE Transactions on Power Systems.

[25]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[26]  Paulin Jacquot,et al.  Peer-to-Peer Electricity Market Analysis: From Variational to Generalized Nash Equilibrium , 2018, Eur. J. Oper. Res..

[27]  Jean-François Toubeau,et al.  Improved day-ahead predictions of load and renewable generation by optimally exploiting multi-scale dependencies , 2017, 2017 IEEE Innovative Smart Grid Technologies - Asia (ISGT-Asia).

[28]  Tianshu Bi,et al.  Smart control for battery energy storage system in a community grid , 2014, 2014 International Conference on Power System Technology.

[29]  Luisa Jorge,et al.  EDPD’s experience with data analytics and stochastic simulation methods for risk-controlled network planning , 2018 .

[30]  Youbing Zhang,et al.  Lyapunov Optimization Based Online Energy Flow Control for Multi-energy Community Microgrids , 2019, 2019 IEEE PES GTD Grand International Conference and Exposition Asia (GTD Asia).

[31]  Alfredo Núñez,et al.  Load profile generator and load forecasting for a renewable based microgrid using Self Organizing Maps and neural networks , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[32]  Francois Vallee,et al.  Cooperative demand‐side management scenario for the low‐voltage network in liberalised electricity markets , 2018, IET Generation, Transmission & Distribution.

[33]  Xiaojun Shen,et al.  A Combined Algorithm for Cleaning Abnormal Data of Wind Turbine Power Curve Based on Change Point Grouping Algorithm and Quartile Algorithm , 2019, IEEE Transactions on Sustainable Energy.

[34]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[35]  Walid Saad,et al.  Managing Price Uncertainty in Prosumer-Centric Energy Trading: A Prospect-Theoretic Stackelberg Game Approach , 2017, IEEE Transactions on Smart Grid.

[36]  Shi You,et al.  The Emergence of Consumer-centric Electricity Markets , 2017 .

[37]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[38]  Tao Hong,et al.  Global energy forecasting competition 2017: Hierarchical probabilistic load forecasting , 2019, International Journal of Forecasting.

[39]  D. Ruppert The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .