State-based load profile generation for modeling energetic flexibility

Communicating the energetic flexibility of distributed energy resources (DERs) is a key requirement for enabling explicit and targeted requests to steer their behavior. The approach presented in this paper allows the generation of load profiles that are likely to be feasible, which means the load profiles can be reproduced by the respective DERs. It also allows to conduct a targeted search for specific load profiles. Aside from load profiles for individual DERs, load profiles for aggregates of multiple DERs can be generated. We evaluate the approach by training and testing artificial neural networks (ANNs) for three configurations of DERs. Even for aggregates of multiple DERs, ratios of feasible load profiles to the total number of generated load profiles of over 99% can be achieved. The trained ANNs act as surrogate models for the represented DERs. Using these models, a demand side manager is able to determine beneficial load profiles. The resulting load profiles can then be used as target schedules which the respective DERs must follow.

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

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

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

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

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

[8]  Hartmut Schmeck,et al.  Modeling flexibility using artificial neural networks , 2018 .

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

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

[11]  H. ElMaraghy.  Enabling Manufacturing Competitiveness and Economic Sustainability , 2012 .

[12]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

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

[14]  José R. Vázquez-Canteli,et al.  Reinforcement learning for demand response: A review of algorithms and modeling techniques , 2019, Applied Energy.

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

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

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

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

[19]  Chen Lu,et al.  A review of stochastic battery models and health management , 2017 .

[20]  Aidan Duffy,et al.  The Generation of Domestic Electricity Load Profiles through Markov Chain Modelling , 2010 .

[21]  Daniel Stetter,et al.  Flexibility Definition for Smart Grid Cells in a Decentralized Energy System , 2018, SMARTGREENS.

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

[23]  Edward A. Lee,et al.  Control Improvisation with Probabilistic Temporal Specifications , 2016, 2016 IEEE First International Conference on Internet-of-Things Design and Implementation (IoTDI).

[24]  Giuseppe Tommaso Costanzo,et al.  A System Architecture for Autonomous Demand Side Load Management in Smart Buildings , 2012, IEEE Transactions on Smart Grid.

[25]  Gunther Reinhart,et al.  A Petri-net Based Approach for Evaluating Energy Flexibility of Production Machines , 2014 .

[26]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[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]  A. Kwasinski,et al.  Development of a Markov-Chain-Based Energy Storage Model for Power Supply Availability Assessment of Photovoltaic Generation Plants , 2013, IEEE Transactions on Sustainable Energy.

[29]  Michael Sonnenschein,et al.  Support vector based encoding of distributed energy resources' feasible load spaces , 2010, 2010 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe).

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

[31]  Tarik A. Rashid,et al.  Auto-regressive Recurrent Neural Network Approach for Electricity Load Forecasting , 2007 .

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

[33]  Gerard J. M. Smit,et al.  Generation of flexible domestic load profiles to evaluate Demand Side Management approaches , 2016, 2016 IEEE International Energy Conference (ENERGYCON).

[34]  Sebastian Lehnhoff,et al.  Phase-Space Sampling of Energy Ensembles with CMA-ES , 2018, EvoApplications.

[35]  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 .

[36]  Michael Sonnenschein,et al.  Constraint-handling for Optimization with Support Vector Surrogate Models - A Novel Decoder Approach , 2013, ICAART.