Abstract
Recent commitments and consequent advances towards an effective energy transition are resulting in promising solutions but also bringing out significant new challenges. Models for energy management at the building and microgrid level are benefiting from new findings in distinct areas such as the internet of things or machine learning. However, the interaction and complementarity between such physical and virtual environments need to be validated and enhanced through dedicated platforms. This chapter presents the Multi-Agent based Real-Time Infrastructure for Energy (MARTINE), which provides a platform that enables a combined assessment of multiple components, including physical components of buildings and microgrids, emulation capabilities, multi-agent and real-time simulation, and intelligent decision support models and services based on machine learning approaches. Besides enabling the study and management of energy resources considering both the physical and virtual layers, MARTINE also provides the means for a continuous improvement of the synergies between the Internet of Things and machine learning solutions.

Abstract
Indoor localization systems are an important topic in the field of manufacturing process. A computational infrastructure based on Bluetooth low energy technology with state estimators for filtering is used to localize employees in the shop floor. The researchers' motivation is two-folds: implement an indoor tracking system while promoting manage production time. In this paper, we discuss the first prototype of a localization system adapted to address these goals. Experimental results show that the system for our case study, achieves a localization accuracy of less than three meters. © 2022 IEEE.

Abstract
Over the years, many techniques have been developed for the stabilisation of bone fractures. The study of the adhesion of bone-to-bone cement is an important step towards the development of new immobilization systems. Although bone cement has been used for more than fifty years, very few studies have been performed regarding the evaluation of fracture properties. In this work, numerical and experimental investigations were conducted to evaluate the strain energy release rate under mode I loading in a bone-cement bonded joint, using the Double Cantilever Beam (DCB) test. Cohesive zone laws were also measured combining the finite element method with non-linear elastic fracture mechanics. This has been made in a cortical bone bonded joint with polymethylmethacrylate (PMMA). Consistent results have been obtained regarding fracture toughness in a widely used bone-to-bone cement joint in many biomedical applications.

Abstract
Future power systems encourage the use of renewable energy resources, among them wind power is of great interest, but its power output is intermittent in nature which can affect the stability of the power system and increase the risk of blackouts. Therefore, a forecasting model of the wind speed is essential for the optimal operation of a power supply with an important share of wind energy conversion systems. In this paper, two wind speed forecasting models based on multiple meteorological measurements of wind speed and temperature are proposed and compared according to their mean squared error (MSE) value. The first model concerns the artificial intelligence based on neural network (ANN) where several network configurations are proposed to achieve the most suitable structure of the problem, while the other model concerned the Adaptive Neuro-Fuzzy Inference System (ANFIS). To enhance the results accuracy, the invalid input samples are filtered. According to the computational results of the two models, the ANFIS has delivered more accurate outputs characterized by a reduced mean squared error value compared to the ANN-based model.

Abstract
Precision fertilization implies the need to identify the variability of soil fertility, which is costly and time-consuming. Remotely measured data can be a solution. Using this strategy, a study was conducted, in a vineyard, to delineate different management zones using two indicators: apparent soil electrical conductivity (ECa) and normalized difference vegetation index (NDVI). To understand the contribution of each indicator, three scenarios were used for zone definition: (1) using only NDVI, (2) only ECa, or (3) using a combination of the two. Then the differences in soil fertility between these zones were assessed using simple statistical methods. The results indicate that the most beneficial strategy is the combined use of the two indicators, as it allowed the definition of three distinct zones regarding important soil variables and crop nutrients, such as soil total nitrogen, Mg2+ cation, exchange acidity, and effective cation exchange capacity, and some relevant cation ratios. This strategy also allowed the identification of an ionic unbalance in the soil chemistry, due to an excess of Mg2+, that was harming crop health, as reported by NDVI. This also impacted ECa and NDVI relationship, which was negative in this study. Overall, the results demonstrate the advantages of using remotely sensed data, mainly more than one type of sensing data, and suggest a high potential for differential crop fertilization and soil management in the study area.

Abstract
Distribution grids currently face news paradigms where Power Quality (PQ) has become one of the most important aspects for distribution system operators (DSO) and consumers. To ensure a PQ within the limits defined by international standards, there is a permanent need to monitor all parameters associated with the distributed voltage by the grid. This task is carried out using the installation of Power Quality Monitors (PQM) at strategic points of the grid. The main aim of this paper is to define a methodology to optimize the best location for the PQM installation. To achieve this target the Monitor Reach Area (MRA) matrix is calculated and an Integer Linear Programming (ILP) optimization model was used to find the best solution. Two case studies were carried out, in which residual voltage values were observed when three-phase short circuits are applied to all nodes. The results obtained show the good effectiveness of the developed method, presenting solutions that allow the total monitoring of the studied networks, using the smallest possible number of PQMs. In this way, it is possible for the DSO to keep the network monitored in real-time with huge efficiency gains. © 2022, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.