Computational Energy Management in Smart Grids

As the world population increases, the sustainable usage of natural resources becomes an issue that humanity and technology are urgently asked to face. Energy represents a relevant example from this perspective and the strong demand coming from developed and developing countries shoved the scientists worldwide to intensify their studies on renewable energy resources. At the same time, due to the increasing complexity of medium and low voltage distribution grids on which distributed electrical generators based on renewables have to be included, a growing interest has been oriented to the development of smart systems able to optimally manage the usage and the distribution of energy among the population with the objective of minimizing energy consumption with economic impact, even at family consumption level. This yielded in a flourishing scientific literature on sophisticated algorithms and systems aimed at introducing intelligence within the electrical energy grid, with several effective solutions already available in the market. The same applies also to the water and gas grids, which share similar peculiarities with the electrical grid. The task is surely challenging and multi-faceted. Indeed the different needs of the heterogeneous grid costumers and the different peculiarities of energy sources to be included in the grid itself have to be taken into account. Moreover several ways of intervention are feasible, as indicated in the US Energy Independence and Security Act of 2007, like: self-healing capability, faulttolerance on resisting attack, integration of all energy generation and storage, dynamic optimization of grid operation and resources with full cyber-security, incorporation of demand-response, demand-side resources and energy-efficient resources, active client participation in the grid operations by providing timely information and control options, improvement of reliability, power quality, security and efficiency of the electricity infrastructure. A multi-disciplinary coordinated action is nowadays required to the scientific communities operating in the Electrical and Electronic Engineering, Computational Intelligence, Digital Signal Processing and Telecommunications research fields to provide adequate technological solutions to these issues, having in mind the more and more stringent constraints in terms of environmental sustainability. The present Special Issue has to be considered from this perspective. It is fully devoted to the exploration of the most recent and stimulating advances within the area of Computational Energy Management in Smart Grids, i.e., the employment of Computational Intelligence techniques for the optimal usage and management of energy resources in Smart Grid applicative scenarios. It collects sixteen original contributions, which cover some of the aforementioned topics providing to the reader an insightful panoramic view of the research achievements and open issues in the field of interest. The present papers are the result of a rigorous review procedure applied to the twenty-three articles initially submitted. At least three independent experts have been involved for each paper (more than seventy in total), and up to three review rounds have been performed before final acceptance for publication. We would like to add that six of the included papers are the extended versions of papers originally submitted and accepted for presentation at the Computational Energy Management in Smart Grids 2014 Workshop (CEMiSG2014), held in Beijng, China, on July 8–9 2014, as inside the International Joint Conference on Neural Networks 2014 (IJCNN2014). These are the papers by Giantomassi et al., Ribeiro et al., Chen at al., He et al., Guo et al., and Fagiani et al., addressed in this order within the following brief presentation of all Special Issue articles. The first contribution of the Issue is by Galvan-Lopez et al., who focalize on the demand-side management (DSM) problem. One of the widely used DSM approaches consists in modulating energy consumption at the customer side of the meter using price incentives. Current incentive schemes allow consumers to reduce their costs, but do not lead to optimal demand patterns. In the context of charging fleets of electric vehicles, the authors propose a centralized method for setting overnight charging schedules. This method uses evolutionary algorithms to automatically search for optimal plans, representing both the charging schedule and the energy drawn from the grid at each time-step. In performed computer simulations, the proposed centralized method achieves improvements with respect to simple models based noncentralized consumer behavior.