Modeling flexibility using artificial neural networks

The flexibility of distributed energy resources (DERs) can be modeled in various ways. Each model that can be used for creating feasible load profiles of a DER represents a potential model for the flexibility of that particular DER. Based on previous work, this paper presents generalized patterns for exploiting such models. Subsequently, the idea of using artificial neural networks in such patterns is evaluated. We studied different types and topologies of ANNs for the presented realization patterns and multiple device configurations, achieving a remarkably precise representation of the given devices in most of the cases. Overall, there was no single best ANN topology. Instead, a suitable individual topology had to be found for every pattern and device configuration. In addition to the best performing ANNs for each pattern and configuration that is presented in this paper all data from our experiments is published online. The paper is concluded with an evaluation of a classification based pattern using data of a real combined heat and power plant in a smart building.

[1]  Renato Machado Monaro,et al.  Active demand side management for households in smart grids using optimization and artificial intelligence , 2018 .

[2]  A. Faruqui,et al.  Quantifying Customer Response to Dynamic Pricing , 2005 .

[3]  Oliver Kramer,et al.  Generalized cascade classification model with customized transformation based ensembles , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

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

[5]  Eberhard Waffenschmidt.  Cellular Power Grids for a 100 % Renewable Energy Supply , 2017 .

[6]  Ronnie Belmans,et al.  Assessing the reflectivity of residential grid tariffs for a user reaction through photovoltaics and battery storage , 2015 .

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

[8]  Peter Palensky,et al.  Demand Side Management: Demand Response, Intelligent Energy Systems, and Smart Loads , 2011, IEEE Transactions on Industrial Informatics.

[9]  Haimonti Dutta,et al.  NILMTK: an open source toolkit for non-intrusive load monitoring , 2014, e-Energy.

[10]  Hartmut Schmeck,et al.  Response of smart residential buildings with energy management systems to price deviations , 2015, 2015 IEEE Innovative Smart Grid Technologies - Asia (ISGT ASIA).

[11]  Carlos Cardeira,et al.  The Daily and Hourly Energy Consumption and Load Forecasting Using Artificial Neural Network Method: A Case Study Using a Set of 93 Households in Portugal☆ , 2014 .

[12]  Mohamed Abuella,et al.  Solar power forecasting using artificial neural networks , 2015, 2015 North American Power Symposium (NAPS).

[13]  Albert Molderink,et al.  On the three-step control methodology for smart grids , 2008 .

[14]  Hartmut Schmeck,et al.  Utilizing Flexibility of Hybrid Appliances in Local Multi-modal Energy Management , 2017 .

[15]  Johann L. Hurink,et al.  Energy management with TRIANA on FPAI , 2015, 2015 IEEE Eindhoven PowerTech.

[16]  Oliver Kramer,et al.  Classification Cascades of Overlapping Feature Ensembles for Energy Time Series Data , 2015, DARE.

[17]  Geert Deconinck,et al.  Applying machine learning techniques for forecasting flexibility of virtual power plants , 2016, 2016 IEEE Electrical Power and Energy Conference (EPEC).

[18]  Ian A. Hiskens,et al.  Achieving Controllability of Electric Loads , 2011, Proceedings of the IEEE.

[19]  Murray Thomson,et al.  High-resolution stochastic integrated thermal–electrical domestic demand model , 2016 .

[20]  Wolfgang Reif,et al.  Robust Scheduling in a Self-Organizing Hierarchy of Autonomous Virtual Power Plants , 2014, ARCS Workshops.

[21]  Pascal Benoit,et al.  Design of a Multiagent‐Based Voltage Control System in Peer‐to‐Peer Networks for Smart Grids , 2014 .

[22]  Sebastian Lehnhoff,et al.  Hybrid Multi-ensemble Scheduling , 2017, EvoApplications.

[23]  Hartmut Schmeck,et al.  Towards the Modeling of Flexibility Using Artificial Neural Networks in Energy Management and Smart Grids: Note , 2018, e-Energy.

[24]  Mladen Kezunovic,et al.  Voltage Stability Prediction Using Active Machine Learning , 2017, IEEE Transactions on Smart Grid.

[25]  Michael Sonnenschein,et al.  A distributed combinatorial optimisation heuristic for the scheduling of energy resources represented by self-interested agents , 2017, Int. J. Bio Inspired Comput..

[26]  A. Faruqui,et al.  Household response to dynamic pricing of electricity: a survey of 15 experiments , 2010 .

[27]  Francesco Piazza,et al.  Energy management with the support of dynamic pricing strategies in real micro-grid scenarios , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[28]  Yoshua Bengio,et al.  Generative Adversarial Networks , 2014, ArXiv.

[29]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[30]  Hartmut Schmeck,et al.  Definition, Modeling, and Communication of Flexibility in Smart Buildings and Smart Grid , 2017 .

[31]  Michael Sonnenschein,et al.  Model-based integration of constrained search spaces into distributed planning of active power provision , 2013, Comput. Sci. Inf. Syst..

[32]  C.W. Gellings,et al.  The concept of demand-side management for electric utilities , 1985, Proceedings of the IEEE.

[33]  Michael Sonnenschein,et al.  Encoding distributed search spaces for virtual power plants , 2011, 2011 IEEE Symposium on Computational Intelligence Applications In Smart Grid (CIASG).

[34]  Astrid Nieße,et al.  Local soft constraints in distributed energy scheduling , 2016, 2016 Federated Conference on Computer Science and Information Systems (FedCSIS).

[35]  Oliver Kramer,et al.  Instance Selection and Outlier Generation to Improve the Cascade Classifier Precision , 2016, ICAART.