As world energy shifts from demand-led to supply-constrained, advancements in information and communication technologies (ICT) are brought to bear on shaping demand at the nodal level and in ways that intrinsic volatility does not threaten the security of an energy system. Towards that end, coupling power systems with information technologies have converted traditional electric energy delivery infrastructures into a hybrid energy-data system (smart grid) that controls power flow via information signals. Hence, grid entities are exposed to multiple heterogeneous data streams coming from various sources, while being engaged to make real-time decisions regarding their load demand and consumption behavior. Dynamic data-driven control is identified as a means of affecting power behavior through incentive signals found in information vectors that include anticipations of future demand (referred to as smart power systems).

The focus of this issue will be on intelligent methods to allow management of power systems and promote real-time decision making for load demand in a dynamically data-driven and varying environment. Specifically, the interest lies in methods that take into consideration the utilization of artificial intelligence tools such as neural networks, kernel machines, clustering and deep learners, either as independent tools or in novel synergistic frameworks for building advanced data analytics.

The issue welcomes submissions in any methods that promote intelligent decision making and data analytics that apparently promote the notion of smart power systems and smart grids.

Dr. Miltos Alamaniotis
Guest Editor