Abstract
High penetration of Photovoltaic (PV) systems, a variable resource, poses challenges to the stability and power quality of electrical grids. Forecasting accurately the PV power has been recognized as a way to ease this problem. This work addresses now-casting of PV power with Extreme Learning Machines (ELMs) without exogenous inputs. Wavelet decomposition and multi-resolution analysis is the most effective way to achieve high accuracy for 5 min-ahead forecast up to 70% greater than the persistence model. A neural network evaluation algorithm based on multiple initializations and incremental hidden nodes is applied and ELMs performance and computation efficiency is evaluated versus Time Delay Neural Networks (TDNNs) for time and time-frequency domain forecasting.

Abstract
The introduction of smart end-users is a vital point towards the smart grid vision. In this respect, smart households have drawn significant attention recently. Home energy management systems (HEMS) in smart households and transformer energy management units have different objectives that can sometimes be conflicting. Thus, a novel interactive optimum operating strategy that considers all possible aspects in each smart household together with internal bi-directional power flows within the household structure from economic (minimization of household daily electricity usage costs) and technical (avoidance of transformer overloading) perspective is proposed in this study. To the best knowledge of the authors, this is the first study in the literature combining all of the possible operational possibilities in HEMS of smart households together with internal household bi-directional power flows and the technical limitations of a transformer unit serving a neighborhood of smart households under a mixed-integer linear programming (MILP) framework.

Abstract
This paper discusses the current Brazilian electricity market, brings out some dilemmas that should be examined in order to implement a more market-oriented approach, and describes a new market design to overcome these issues. The proposed market design is based on virtual reservoirs and aims at enhancing the flexibility to enable market participants to comply with their contracts, while still ensuring the efficient use of the water and maintaining the current level of the security of supply. In addition, to simulate the behavior of the market participants in this new framework, an Agent-Based Model ABM where agents use reinforcement Q-Learning - is developed and applied to a case study that includes a centralized dispatch as currently exists in Brazil. The results obtained so far show that this new design is suitable to allow hydros managing their commercial contract commitments with extra flexibility.

Abstract
During the last decades, the radioactive noble gas radon has found a variety of geoscientific applications, ranging from its utilization as a potential earthquake precursor and proxy of tectonic stress over its specific role in volcanic environments to a wide range of applications as a tracer in marine and hydrological settings. This topical issue summarizes the current state of research as exemplified by some original research articles covering the aforementioned as well as other closely related aspects and points to some important future directions of radon application in geosciences. This editorial provides a more detailed overview of the contents of this volume, a brief summary of the rationale underlying the diverse applications, and outlines some important perspectives.

Abstract
Driving simulators require extensive road environments, with roads correctly modeled and similar to those found in real world. The modeling of extensive road environments, with the specific characteristics required by driving simulators, may result in a long time consuming process. This paper presents a procedural method to the modeling of large road environments. The proposed method can produce a road network design to populate an empty terrain and produce all the related road environment models. The terrain model can also be edited to produce well-constructed road environments. The road and terrain models are optimized to interactive visualization in real time, applying all the stet-of-art techniques like the level of detail selection. The proposed method allows modeling large road environments, with the realism and quality required to the realization of experimental work in driving simulators.

Abstract
This paper proposes the development of biologically inspired robots as the capstone project of the European Project Semester (EPS) framework. EPS is a one semester student centred international programme offered by a group of European engineering schools (EPS Providers) as part of their student exchange programme portfolio. EPS is organized around a central module (the EPS project) and a set of complementary supportive modules. Project proposals refer to open multidisciplinary real world problems. Its purpose is to expose students to problems of a greater dimension and complexity than those faced throughout the degree programme as well as to put them in contact with the so-called real world, in opposition to the academic world. Students are organized in teams, grouping individuals from diverse academic backgrounds and nationalities, and each team is fully responsible for conducting its project. EPS provides an integrated framework for undertaking capstone projects, which is focused on multicultural and multidisciplinary teamwork, communication, problem-solving, creativity, leadership, entrepreneurship, ethical reasoning and global contextual analysis. The design and development of biologically inspired robots allows the students to fulfil the previously described requirements and objectives and, as a result, we recommend the adoption of these projects within the EPS project capstone module for the benefit of engineering students.