Towards the Modeling of Flexibility Using Artificial Neural Networks in Energy Management and Smart Grids: Note

ABSTRACT

This paper presents a novel approach to the representation and communication of the energy flexibility of distributed energy resources. The approach uses artificial neural networks (ANNs) to represent the devices and act as surrogate models. The main benefit of this approach is its potential to represent arbitrary energy flexibilities and the resulting universal applicability in various usage patterns, some of which are presented in detail in this paper. Furthermore, the flexibility represented by an ANN can be conditioned on the state of the corresponding devices and their environment, such that only a small state update needs to be communicated to construct feasible load profiles by a third party. Therefore, in contrast to other approaches, such as support vector data description, new ANNs only need to be constructed once the device configuration changes.

References

1. G. Anders, A. Schiendorfer, J. P. Steghoefer, and W. Reif. 2014. Robust Scheduling in a Self-Organizing Hierarchy of Autonomous Virtual Power Plants. In ARCS 2014; 2014 Workshop Proceedings on Architecture of Computing Systems. 1--8.
2. Lukas Barth, Nicole Ludwig, Esther Mengelkamp, and Philipp Staudt. 2017. A comprehensive modelling framework for demand side flexibility in smart grids. Computer Science-Research and Development (2017), 1--11.
3. Nipun Batra, Jack Kelly, Oliver Parson, Haimonti Dutta, William Knottenbelt, Alex Rogers, Amarjeet Singh, and Mani Srivastava. 2014. NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring. In Proceedings of the 5th International Conference on Future Energy Systems (e-Energy '14). ACM, 265--276.
4. N. Blaauwbroek, P.H. Nguyen, M.J. Konsman, Huaizhou Shi, R.I.G. Kamphuis, and W.L. Kling. 2015. Decentralized Resource Allocation and Load Scheduling for Multicommodity Smart Energy Systems. IEEE Transactions on Sustainable Energy 6, 4 (2015), 1506--1514.
5. Jörg Bremer and Sebastian Lehnhoff. 2017. Hybrid Multi-ensemble Scheduling. In Applications of Evolutionary Computation: 20th European Conference, EvoApplications 2017, Proceedings, Part I, Giovanni Squillero and Kevin Sim (Eds.), Vol. 10199. Springer International Publishing, 342--358.
6. J. Bremer, B. Rapp, and M. Sonnenschein. 2011. Encoding distributed search spaces for virtual power plants. In 2011 IEEE Symposium on Computational Intelligence Applications In Smart Grid (CIASG). 1--8.
7. Jörg Bremer and Michael Sonnenschein. 2013. Model-based Integration of Constrained Search Spaces into Distributed Planning of Active Power Provision. Computer Science & Information Systems 10, 4 (2013), 1823--1854.
8. D.S. Callaway and I.A. Hiskens. 2011. Achieving Controllability of Electric Loads. Proc. IEEE 99, 1 (2011), 184--199.
9. B. Daryanian, Roger E. Bohn, and R.D. Tabors. 1991. An experiment in real time pricing for control of electric thermal storage systems. IEEE Transactions on Power Systems 6, 4 (1991), 1356--1365.
10. Ahmad Faruqui and Stephen George. 2005. Quantifying Customer Response to Dynamic Pricing. The Electricity Journal 18, 4 (2005), 53--63.
11. Ahmad Faruqui and Sanem Sergici. 2010. Household response to dynamic pricing of electricity: a survey of 15 experiments. Journal of Regulatory Economics 38, 2 (2010), 193--225.
12. Jiří Fink and Johann L. Hurink. 2015. Minimizing costs is easier than minimizing peaks when supplying the heat demand of a group of houses. European Journal of Operational Research 242, 2 (2015), 644--650.
13. C.W. Gellings. 1985. The concept of demand-side management for electric utilities. Proc. IEEE 73, 10 (1985), 1468--1470.
14. Girish Ghatikar, Salman Mashayekh, Michael Stadler, Rongxin Yin, and Zhenhua Liu. 2016. Distributed energy systems integration and demand optimization for autonomous operations and electric grid transactions. Applied Energy 167 (2016), 432--448.
15. Hans Christian Gils, Yvonne Scholz, Thomas Pregger, Diego Luca de Tena, and Dominik Heide. 2017. Integrated modelling of variable renewable energy-based power supply in Europe. Energy 123, Supplement C (2017), 173--188.
16. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Networks. arXiv:1406.2661 {cs, stat} (June 2014). http://arxiv.org/abs/1406.2661 arXiv: 1406.2661.
17. Sebastian Gottwalt. 2015. Managing Flexible Loads in Residential Areas. Ph.D. Dissertation. Karlsruhe Institute of Technology (KIT).
18. Hassan Harb, Jan-Niklas Paprott, Peter Matthes, Thomas Schütz, Rita Streblow, and Dirk Müller. 2015. Decentralized scheduling strategy of heating systems for balancing the residual load. Building and Environment 86 (2015), 132--140.
19. K. Heussen, S. Koch, A. Ulbig, and G. Andersson. 2010. Energy storage in power system operation: The power nodes modeling framework. In 2010 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe). 1--8.
20. Christian Hinrichs, Ute Vogel, and Michael Sonnenschein. 2011. Approaching decentralized demand side management via self-organizing agents. In Proceedings of 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), ATES Workshop.
21. Christian Hirsch. 2015. Fahrplanbasiertes Energiemanagement in Smart Grids. Ph.D. Dissertation. Karlsruhe Institute of Technology (KIT).
22. M. Hoefling, F. Heimgaertner, M. Menth, and H. Bontius. 2015. Traffic estimation of the PowerMatcher application for demand supply matching in smart grids. In 2015 International Conference and Workshops on Networked Systems (NetSys). 1--6.
23. F. Kazhamiaka, C. Rosenberg, and S. Keshav. 2016. Practical Strategies for Storage Operation in Energy Systems: Design and Evaluation. IEEE Transactions on Sustainable Energy 7, 4 (2016), 1602--1610.
24. Sebastian Kochanneck, Hartmut Schmeck, Ingo Mauser, and Birger Becker. 2015. Response of Smart Residential Buildings with Energy Management Systems to Price Deviations. In 2015 IEE Proceedings of the IEEE PES Conference on Innovative Smart Grid Technologies Asia (ISGT-Asia).
25. J. K. Kok, C. J. Warmer, and I. G. Kamphuis. 2005. PowerMatcher: Multiagent Control in the Electricity Infrastructure. In 2005 AAMAS. 75--82.
26. T. Krause, G. Andersson, K. Fröhlich, and A. Vaccaro. 2011. Multiple-Energy Carriers: Modeling of Production, Delivery, and Consumption. Proc. IEEE 99, 1 (2011), 15--27.
27. V. Malbasa, C. Zheng, P. C. Chen, T. Popovic, and M. Kezunovic. 2017. Voltage Stability Prediction Using Active Machine Learning. IEEE Transactions on Smart Grid 8, 6 (2017), 3117--3124.
28. Ingo Mauser. 2017. Multi-modal Building Energy Management. Ph.D. Dissertation. Karlsruhe Institute of Technology (KIT).
29. Ingo Mauser, Jan Müller, Florian Allerding, and Hartmut Schmeck. 2016. Adaptive Building Energy Management with Multiple Commodities and Flexible Evolutionary Optimization. Renewable Energy 87, Part 2 (2016), 911--921.
30. Ingo Mauser, Jan Müller, Kevin Förderer, and Hartmut Schmeck. 2017. Definition, Modeling, and Communication of Flexibility in Smart Buildings and Smart Grids. In ETG-Fb. 155: International ETG Congress 2017. VDE Verlag, 605--610.
31. Ingo Mauser, Jan Müller, and Hartmut Schmeck. 2017. Utilizing Flexibility of Hybrid Appliances in Local Multi-modal Energy Management. In Proceedings of the 9th International Conference EEDAL'2017 -- Energy Efficiency in Domestic Appliances and Lighting. Publications Office of the European Union.
32. A. Mishra, D. Irwin, P. Shenoy, J. Kurose, and T. Zhu. 2013. GreenCharge: Managing RenewableEnergy in Smart Buildings. IEEE Journal on Selected Areas in Communications 31, 7 (2013), 1281--1293.
33. A.-H. Mohsenian-Rad, V.W.S. Wong, J. Jatskevich, R. Schober, and A. Leon-Garcia. 2010. Autonomous Demand-Side Management Based on Game-Theoretic Energy Consumption Scheduling for the Future Smart Grid. IEEE Transactions on Smart Grid 1, 3 (2010), 320--331.
34. A. Molderink. 2011. On the three-step control methodology for Smart Grids. Ph.D. Dissertation. University of Twente.
35. A. Molderink, V. Bakker, M.G.C. Bosman, J.L. Hurink, and G.J.M. Smit. 2010. Management and Control of Domestic Smart Grid Technology. IEEE Transactions on Smart Grid 1, 2 (2010), 109--119.
36. J. Neugebauer, J. Bremer, C. Hinrichs, O. Kramer, and M. Sonnenschein. 2016. Generalized cascade classification model with customized transformation based ensembles. In 2016 International Joint Conference on Neural Networks (IJCNN). 4056--4063.
37. Judith Neugebauer, Oliver Kramer, and Michael Sonnenschein. 2015. Classification Cascades of Overlapping Feature Ensembles for Energy Time Series Data. In Data Analytics for Renewable Energy Integration, Wei Lee Woon, Zeyar Aung, and Stuart Madnick (Eds.). Springer International Publishing, 76--93.
38. Judith Neugebauer, Oliver Kramer, and Michael Sonnenschein. 2017. Instance Selection and Outlier Generation to Improve the Cascade Classifier Precision. Springer International Publishing, 151--170.
39. Bijay Neupane, Laurynas Šikšnys, and Torben Bach Pedersen. 2017. Generation and Evaluation of Flex-Offers from Flexible Electrical Devices. In Proceedings of the Eighth International Conference on Future Energy Systems (e-Energy '17). ACM, 143--156.
40. A. Nieße, M. Sonnenschein, C. Hinrichs, and J. Bremer. 2016. Local soft constraints in distributed energy scheduling. In 2016 Federated Conference on Computer Science and Information Systems (FedCSIS). 1517--1525.
41. OpenADR Alliance. 2013. OpenADR 2.0 -- Profile Specification -- B Profile -- Rev.: 1.0. online. (2013).
42. Peter Palensky and Dietmar Dietrich. 2011. Demand Side Management: Demand Response, Intelligent Energy Systems, and Smart Loads. IEEE Transactions on Industrial Informatics 7, 3 (2011), 381--388.
43. A. De Paola, D. Angeli, and G. Strbac. 2017. Price-Based Schemes for Distributed Coordination of Flexible Demand in the Electricity Market. IEEE Transactions on Smart Grid 8, 6 (2017), 3104--3116.
44. Y. Riffonneau, S. Bacha, F. Barruel, and S. Ploix. 2011. Optimal Power Flow Management for Grid Connected PV Systems With Batteries. IEEE Transactions on Sustainable Energy 2, 3 (2011), 309--320.
45. Fredy Rios. 2016. Stigmergy-based load scheduling in a demand side management context. Ph.D. Dissertation. Karlsruhe Institute of Technology (KIT).
46. Gregor Rohbogner, Simon Fey, Pascal Benoit, Christof Wittwer, and Andreas Christ. 2014. Design of a Multiagent-Based Voltage Control System in Peer-to-Peer Networks for Smart Grids. Energy Technology 2, 1 (2014), 107--120.
47. Katia Gregio Di Santo, Silvio Giuseppe Di Santo, Renato Machado Monaro, and Marco Antonio Saidel. 2018. Active demand side management for households in smart grids using optimization and artificial intelligence. Measurement 115, Supplement C (2018), 152--161.
48. M. Severini, S. Squartini, M. Fagiani, and F. Piazza. 2015. Energy management with the support of dynamic pricing strategies in real micro-grid scenarios. In 2015 International Joint Conference on Neural Networks (IJCNN). 1--8.
49. Hermen A. Toersche, Johann L. Hurink, and Mente J. Konsman. 2015. Energy management with TRIANA on FPAI. In 2015 IEEE PowerTech.
50. Tea Tusar, E. Dovgan, and Bogdan Filipic. 2012. Evolutionary scheduling of flexible offers for balancing electricity supply and demand. In 2012 IEEE Congress on Evolutionary Computation (CEC). 1--8.
51. A. Veit and H.-A. Jacobsen. 2015. Multi-agent device-level modeling framework for demand scheduling. In 2015 IEEE International Conference on Smart Grid Communications (SmartGridComm). 169--174.
52. ZigBee+HomePlug Joint Working Group. 2013. Smart Energy Profile 2 -- Application Protocol Standard -- ZigBee Public Document 13-0200-00. (2013).

Index Terms

• Computer systems organization

  • Embedded and cyber-physical systems

• Computing methodologies

  • Machine learning

  • Modeling and simulation

• Hardware

  • Power and energy

    • Energy distribution

      • Smart grid