Abstract
Electrical grids are traditionally operated as multi-entity systems with each entity managing a geographical region. The current movement toward energy democratization and decarbonization is resulting in the growing penetration of controllable energy resources. This process in turn is increasing the number of grid entities (agents). The paradigm shift is also fueled by the increased adoption of intelligent sensors and actuators for advanced processing and computing. While collaboration among agents reduces costs and increases overall reliability, effective collaboration is challenging. The main challenges stem from the heterogeneity of agents and their data. Furthermore, while data collection is constantly increasing many grid entities have strict privacy requirements that limit data usage. Another challenge is the energy industry’s usual practice of keeping data in silos. Deep learning and federated computations are well suited to addressing these issues. Deep learning enables predicting energy needs and profiling agents’ energy profiles. Through federated computation, agents collaboratively solve learning and optimization problems while preserving privacy and overcoming cross-device and cross-organization data isolation. This chapter discusses the practical challenges of performing multi-agent data processing. It then addresses issues of coordinating connected distributed energy resources (DERs) in the Internet of Things (IoT). Finally, the chapter’s case studies demonstrate how these techniques can address load forecasting and coordination challenges.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Thornburg, J., Krogh, B., Ustun, T.S.: “Stochastic simulator for smart microgrid planning. In: Association for Computing Machinery Symposium on Computing and Development. Nairobi, Kenya (2016)
Keshan, J, Thornburg, and T. S. Ustun, “Comparison of lead-acid and lithium ion batteries for stationary storage in off-grid energy systems. in IET International Conference on Clean Energy and Technology, Nov. 2016
J. Mohammadi, “Distributed computational methods for energy management in smart grids,” Ph.D. dissertation, Carnegie Mellon University, 2016
J. Thornburg, “A tool for probabilistic evaluation of microgrid operating strategies with demand side management,” Ph.D. dissertation, Carnegie Mellon University, Dec. 2018
Thornburg, J., Krogh, B.: “Simulating energy management strategies for microgrids with smart meter demand management,” in 2017 IEEE PES PowerAfrica Conference. Accra, Ghana (2017).Jun
Thornburg, J., Ustun, T.S., Krogh, B.: “Smart microgrid operation simulator for management and electrification planning,” in 2016 IEEE PES PowerAfrica Conference. Livingstone, Zambia (2016).Jun
Shariatzadeh, F., Mandal, P., Srivastava, A.K.: Demand response for sustainable energy systems: A review, application and implementation strategy. Renewable and Sustainable Energy Reviews 45, 343–350 (2015)
Mohammadi, J., Thornburg, J.: “Connecting distributed pockets of energy flexibility through federated computations: Limitations and possibilities,” in Proceedings of the IEEE International Conference on Machine Learning and Applications. Florida, Miami (2020).Dec
Dos Santos, F.C., Thornburg, J., Ustun, T.S.: “Automated planning of rooftop PV systems by aerial image processing,” in Proceedings of the IEEE PES Asia-Pacific Power and Energy Engineering Conference. Kota Kinabalu, Malaysia (2018).Oct
M. Babcock, R. E. Ciez, A. Loew, B. Sergi, J. Thornburg, and N. J. Williams, “Institutional influence on power sector investments: A case study of distributed and centralized energy in Kenya and Tanzania,” Energy Research and Social Science, vol. 41, no. C, 4 2018
Kok, K., Widergren, S., Yang, G., Hu, J.: Guest editorial introduction to the special section on transactive approaches to integration of flexible demand and distributed generation. IEEE Transactions on Power Systems 34(5), 3991–3993 (2019)
Tushar, W., et al.: Peer-to-peer trading in electricity networks: an overview. IEEE Transactions on Smart Grid (2020)
A. Imteaj, M. H. Amini, and J. Mohammadi, “Leveraging decentralized artificial intelligence to enhance resilience of energy networks,” arXiv preprint arXiv:1911.07690, 2019
Schiermeier, Q.: Increased flood risk linked to global warming: likelihood of extreme rainfall may have been doubled by rising greenhouse-gas levels. Nature 470(7334), (Feb. 2011)
J. Robbins, “Climate whiplash: Wild swings in extreme weather are on the rise,” Yale Environment 360, Nov. 2019
Holling, C.S.: Resilience and stability of ecological systems. Annual review of ecology and systematics 4(1), 1–23 (1973)
J. Thornburg, G. Hug, T. Ustun, A. Rowe, and B. Krogh, “Incorporating smart-grid operating strategies into off-grid electrification planning,” in SIAM Conference on Control and Its Applications, Jul. 2015
I. Goodfellow, Y. Bengio, A. Courville, and Y. Bengio, Deep learning. MIT press Cambridge, 2016, vol. 1, no. 2
Cevher, V., et al.: Convex optimization for big data: Scalable, randomized, and parallel algorithms for big data analytics. IEEE Signal Processing Magazine 31(5), 32–43 (2014)
Yan, F., et al.: Distributed autonomous online learning: Regrets and intrinsic privacy-preserving properties. IEEE Transactions on Knowledge and Data Engineering 25(11), 2483–2493 (2012)
Chen, J., Sayed, A.H.: Diffusion adaptation strategies for distributed optimization and learning over networks. IEEE Transactions on Signal Processing 60(8), 4289–4305 (2012)
S. Boyd et al., Distributed optimization and statistical learning via the alternating direction method of multipliers. Now Publishers Inc, 2011
J. Mohammadi and S. Kolouri, “Collaborative learning through shared collective knowledge and local expertise,” in 29th International Workshop on Machine Learning for Signal Processing. IEEE, 2019. [Online]. Available: https://doi.org/10.1109/MLSP.2019.8918888
M. Li, D. G. Andersen, A. J. Smola, and K. Yu, “Communication efficient distributed machine learning with the parameter server,” in Advances in Neural Information Processing Systems, 2014, pp. 19–27
Huang, Z., Hu, R., Guo, Y., Chan-Tin, E., et al.: Dp-admm: Admm-based distributed learning with differential privacy. IEEE Transactions on Information Forensics and Security 15, 1002–1012 (2019)
Xing, E.P., Ho, Q., Dai, W., Kim, J.K., Wei, J., Lee, S., Zheng, X., Xie, P., et al.: Petuum: A new platform for distributed machine learning on big data. IEEE Transactions on Big Data 1(2), 49–67 (2015)
P. Kairouz, H. B. McMahan, B. Avent et al., “Advances and open problems in federated learning,” preprint arXiv:1912.04977, Dec. 2019
Li, T., Sahu, A.K., Talwalkar, A., Smith, V.: Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine 37(3), 50–60 (2020)
F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, “Fog computing and its role in the internet of things,” in Proceedings of the first edition of the MCC workshop on Mobile cloud computing, 2012, pp. 13–16
Deshpande, A., Guestrin, C., Madden, S.R., Hellerstein, J.M., Hong, W.: Model-based approximate querying in sensor networks. The VLDB Journal (The International Journal on Very Large Data Bases) 14(4), 417–443 (2005)
P. Garcia Lopez, A. Montresor, D. Epema, A. Datta, T. Higashino, A. Iamnitchi, M. Barcellos, P. Felber, and E. Riviere, “Edge-centric computing: Vision and challenges,” 2015
T. Li, M. Sanjabi, A. Beirami, and V. Smith, “Fair resource allocation in federated learning,” preprint arXiv:1905.10497, 2019
Bao, Z., Cao, Y., Wang, G., Ding, L.: Analysis of cascading failure in electric grid based on power flow entropy. Physics Letters A 373(34), 3032–3040 (2009)
Wood, A.J., Wollenberg, B.F., Sheblé, G.B.: Power generation, operation, and control. John Wiley & Sons (2013)
Widergren, S., Taft, J.D.: Grid architecture: The decisions that will shape our energy future [guest editorial]. IEEE Power and Energy Magazine 17(5), 14–16 (2019)
Stephens, J.C., Burke, M.J., Gibian, B., Jordi, E., et al.: Operationalizing energy democracy: Challenges and opportunities in Vermont’s renewable energy transformation. Frontiers in Communication 3, 43 (2018)
K. Blunt et al., “PG&E starts to cut power for nearly 800,000 California customers on wildfire risk.” Wall Street Journal, Oct. 2019
Smarra, F., et al.: Data-driven model predictive control using random forests for building energy optimization and climate control. Applied Energy 226, 1252–1272 (2018)
Gao, Y., Ruan, Y., Fang, C., Yin, S.: Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data. Energy and Buildings 223, 110156 (2020)
A. Taïk and S. Cherkaoui, “Electrical load forecasting using edge computing and federated learning,” in Proceedings of the IEEE International Conference on Communications (ICC), May 2020
P. A. G. Watson, “Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction,” Journal of Advances in Modeling Earth Systems, vol. 11, no. 5, pp. 1402–1417
Junker, R.G., et al.: Characterizing the energy flexibility of buildings and districts. Applied Energy 225, 175–182 (2018)
Ustun, T.S., Thornburg, J., Krogh, B.: “Smart pricing implementation/simulator with ICT infrastructure,” in Africa-EU Symposium on Renewable Energy Research and Innovation. Tlemcen, Algeria (2016).Mar
A. Imteaj et al., “Federated learning for resource-constrained iot devices: Panoramas and state-of-the-art,” preprintarXiv:2002.10610, 2020
M. Chen et al., “A joint learning and communications framework for federated learning over wireless networks,” preprintarXiv:1909.07972, 2019
F. Chen, M. Luo et al., “Federated meta-learning with fast convergence and efficient communication,” preprintarXiv:1802.07876, 2018
A. Das and T. Brunschwiler, “Privacy is what we care about: Experimental investigation of federated learning on edge devices,” in Proceedings of the First International Workshop on Challenges in AI and ML for Internet of Things, 2019, pp. 39–42
A. Hard, K. Rao, R. Mathews, S. Ramaswamy et al., “Federated learning for mobile keyboard prediction,” preprintarXiv:1811.03604, 2018
McParland, C., “OpenADR open source toolkit: Developing open source software for the Smart Grid,” in, : IEEE PES General Meeting. IEEE 2011, 1–7 (2011)
Ma, C., et al.: Distributed optimization with arbitrary local solvers. Optimization Methods and Software 32(4), 813–848 (2017)
J. Konečnỳ et al., “Federated learning: Strategies for improving communication efficiency,” preprintarXiv:1610.05492, 2016
Mohammadi, J., Hug, G., Kar, S., “Asynchronous distributed approach for dc optimal power flow,” in, : IEEE Eindhoven PowerTech. IEEE 2015, 1–6 (2015)
Olfati-Saber, R., et al.: Consensus and cooperation in networked multi-agent systems. Proceedings of the IEEE 95(1), 215–233 (2007)
J. Kim, C. Goodman, and J. Mohammadi, “CarnegiePLUG: Prosumer-in-the-Loop simUlation Grid,” in Proceedings of the 2020 IEEE 6th World Forum on Internet of Things (WF-IoT), 2020
“The VOLTTRON environment,” U.S. Department of Energy and Pacific Northwest National Laboratory, 2016, retrieved Jan. 12, 2021 from https://volttron.org/
J. Lenard, “U.S. convenience store count,” The Association For Convenience and Fuel Retailing (NACS), 2020
A. Fuller, Z. Fan, C. Day, and C. Barlow, “Digital twin: Enabling technologies, challenges and open research,” IEEE Access, vol. 8, pp. 108 952–108 971, 2020
Liu, M., Fang, S., Dong, H., Xu, C.: Review of digital twin about concepts, technologies, and industrial applications. Journal of Manufacturing Systems (2020)
R. Srinivasan, B. Manohar, and R. Issa, Urban Building Energy CPS (UBE-CPS): Real-Time Demand Response Using Digital Twin. Springer, May 2020
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural computation 9(8), 1735–1780 (1997)
“EnergyPlus,” U.S. Department of Energy, Building Technologies Office, 2020
“Reference buildings by building type: Supermarket,” U.S. DOE Office of Energy Efficiency and Renewable Energy, Dec. 2013
M. G. Edward Barbour, “Enhancing household-level load forecasts using daily load profile clustering,” in BuildSys ’18: Proceedings of the 5th Conference on Systems for Built Environments, Nov. 2018
R. T. de Salis et al., “Energy storage control for peak shaving in a single building,” in 2014 IEEE PES General Meeting | Conference Exposition, 2014, pp. 1–5
Goodman, C., Thornburg, J., Mohammadi, J.: “Optimization of refrigeration defrost schedules for demand shifting in commercial buildings,” in Proceedings of the 2021 IEEE Green Technologies Conference. Denver, Colorado (2021).Apr
“2022 emissions metrics,” Southern California Edison, 2020
“Building climate zones,” California Energy Commission, Aug. 2020
Dichter, M.: What is time dependent valuation (TDV)? University of California Davis, Western Cooling Efficiency Center (2019)
“Commercial reference building: Supermarket,” U.S. Department of Energy, Open Data Catalog, OpenEI, Nov. 2014
“Database for energy efficient resources,” California Public Utilities Commission, Sep. 2020
“OpenStudio,” Alliance for Sustainable Energy, LLC, 2020
“Business rate basics: Rate schedule TOU-GS-2-B for medium-sized businesses,” Southern California Edison, 2014
“Schedule TOU-GS-2: Time-of-use - general service - demand metered,” Southern California Edison, Mar. 2019
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Goodman, C., Thornburg, J., Ramaswami, S.K., Mohammadi, J. (2022). Building Power Grid 2.0: Deep Learning and Federated Computations for Energy Decarbonization and Edge Resilience. In: Wani, M.A., Raj, B., Luo, F., Dou, D. (eds) Deep Learning Applications, Volume 3. Advances in Intelligent Systems and Computing, vol 1395. Springer, Singapore. https://doi.org/10.1007/978-981-16-3357-7_11
Download citation
DOI: https://doi.org/10.1007/978-981-16-3357-7_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3356-0
Online ISBN: 978-981-16-3357-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)