Quantum mechanics

Context (archaeology)

Engineering

Efficient energy use

Biology

Smart grid

Energy (signal processing)

Power (physics)

Computer science

Grid

Distributed computing

Paleontology

Physics

Mathematics

Inference

Data science

Reliability (semiconductor)

Artificial intelligence

Geometry

Electrical engineering

Summary form only given, as follows. The complete presentation was not made available for publication as part of the conference proceedings. The introduction of renewables and the goal of increasing efficiency and reliability is revolutionizing energy grids. Energy grids must become intelligent and be able to manage energy flows and flexibly adapt to changes in production and demand. This paradigm has fostered the creation of new business models on top of technology advances. The physical infrastructure must embed sensing, communication and processing capabilities. This talk will provide an overview of relevant applications (from metering and diagnostics to energy management) and discuss the role of sensing, processing and inference. It will also cover relevant communication technologies to provide connectivity and in particular new applications of power line communication that enable grid diagnostics by processing high frequency signals. In this context, we will also elaborate on the concept of learning the system model and discuss how top-down phenomenological approaches followed by machine learning paradigms can be merged with bottom-up physical domain approaches.

Learning, processing and communication in smart energy grids