Artificial intelligence (AI) and machine learning (ML) have seen limited applications of actionable value in electrical power systems; however, the landscape is drastically changing and unprecedented use cases of high potential have emerged. The widespread deployment of renewable energy resources (RES), to achieve the clean energy transition goals, has raised
many concerns for electrical grid operators and planners. The volatile nature of RES when added to that of load demand has exacerbated the fears of serious instability events, as was the case with the grid of Texas during the 2021 winter storm. Consequently, and rooted in traditional power system engineering, RES are treated conservatively. This approach discounts that
RES could be actively monitored and optimally controlled jointly with conventional resources, storage systems and loads, which defines the paradigm of hybrid renewable energy systems (hRES). AI and ML are fitting tools for the operational control of hRES, due to the volatility and diversity of units within hRES, the complexities of the electrical grid and the restructured electricity market landscape. Two hRES control proposals by AI and ML are presented in this talk. Firstly, with ML, topdown heuristically inducted binary decision trees are used to determine cost-optimal contingency plans for the cases of extreme deficit or excess of power by a hRES – also known as firm capacity control. Such kind of imbalances are usually beyond the typical security measures taken by system operators and can threaten the grid with severe instability. Secondly, via AI, a distribution network is modeled as a physical object with point masses representing currents injected by generation and absorbed by loads. Operating this network or part of it as a hRES, its voltage profile can be improved by counter-balancing the centers of mass of hRES generation with those of loads along the full length of the network and, recursively, smaller segments of it thereof. This method can allow increased RES penetrations as the power quality requirements for voltage are actively handled, instead of assessing them over a singular profile calculated at worst case conditions.
Panayiotis (Panos) Moutis, PhD, is Special Faculty with the Scott Institute for Energy Innovation at Carnegie Mellon University (CMU) since August 2018 (postdoc at Electrical & Computer Engineering, CMU, 2016-18). His recent grants include one from the national system operator of Portugal, REN, for the development of a transmission expansion planning platform,
and another from the moonshot factory of Google, X, for the digital twin of the electrical grid. Between 2018-20 he served as a Marie Curie Research Fellow with DEPsys, Switzerland. In 2014 he was awarded a fellowship by Arup UK (through the University of Greenwich), on the “Research Challenge of Balancing Urban Microgrids in Future Planned Communities”,
whereas in 2013 he won the “IEEE Sustainability 360o Contest” on the topic of Power. Throughout 2007-15, as part of Prof. Nikos Hatziargyriou’s research group he contributed to over a dozen R&D projects funded by the European Commission. Panos received both his diploma (2007) and his PhD (2015) degrees in Electrical & Computer Engineering at the National Technical University of Athens, Greece, and has published more than 30 papers and contributed to 5 book chapters. He has accumulated over 10 years of experience as a technical consultant on projects of Renewable Energy Sources and Energy Efficiency, and serves in energy start-ups as advisor and executive. He is a senior member of multiple IEEE societies, member of the IEEE-USA Energy Policy Committee, associate editor of IEEE & IET scientific journal, task-group chair in two IEEE standards working groups, chair of the IEEE Smart Grid Publications Committee and editor-in-chief of the “IEEE Smart Grid Newsletter”.