Abstract
This paper presents a Support Vector Machine (SVM) based approach for energy consumption forecasting. The proposed approach includes the combination of both the historic log of past consumption data and the history of contextual information. By combining variables that influence the electrical energy consumption, such as the temperature, luminosity, seasonality, with the log of consumption data, it is possible for the proposed method by find patterns and correlations between the different sources of data and therefore improves the forecasting performance. A case study based on real data from a pilot microgrid located at the GECAD campus in the Polytechnic of Porto is presented. Data from the pilot buildings are used, and the results are compared to those achieved by several states of the art forecasting approaches. Results show that the proposed method can reach lower forecasting errors than the other considered methods.

Abstract
This paper introduces a novel strategy for the task of simultaneously locating two key anatomical landmarks in retinal images of the eye fundus, namely the optic disc and the fovea. For that, instead of attempting to classify each pixel as belonging to the background, the optic disc, or the fovea center, which would lead to a highly class-imbalanced setting, the problem is reformulated as a pixelwise regression task. The regressed quantity consists of the distance from the closest landmark of interest. A Fully-Convolutional Deep Neural Network is optimized to predict this distance for each image location, implicitly casting the problem into a per-pixel Multi-Task Learning approach by which a globally consistent distribution of distances across the entire image can be learned. Once trained, the two minimal distances predicted by the model are selected as the locations of the optic disc and the fovea. The joint learning of every pixel position relative to the optic disc and the fovea favors an automatic understanding of the overall anatomical distribution. This results in an effective technique that can detect both locations simultaneously, as opposed to previous methods that handle both tasks separately. Comprehensive experimental results on a large public dataset validate the proposed approach.

Abstract
In active distribution grids (ADNs), a distribution corporation (Disco) can trade electricity with micro-grids (MGs) besides trading electricity with wholesale markets. Therefore, the operational flexibility of the Disco is increased so that it can play as a price-maker agent in electricity markets. To model the actions of Disco, a bi-level optimization method is developed where Disco problem is modeled at the upper-level problem, whereas the MGs problem together with the day-ahead market clearing procedure are modeled as the lower-level problems. To take the stochastic performance of green energy integration and loads into account, the Disco analysis is shown as two-stage stochastic problem, in which the Disco risk aversion is programmed considering the conditional value-at-risk tool. The subsequent non-linear bi-level approach is converted into a linear single-level approach through Karush-Kuhn-Tucker (KKT) conditions and dual theory. To validate the success of the proposed method, a 24-bus power system is used. Conclusions are duly drawn.

Abstract
The European Union (EU) is adopting proactive strategies toward global decarbonization, proposing ambitious climate objectives to the international community, and adopting by itself ambitious energy and climate change objectives, as can be checked in its strategic packages for 2020, 2030 and 2050. As can be seen in these packages and in global climate and energy agreements, renewable generation is a key aspect to reach the global decarbonizing objectives. This chapter starts with a review of the very basic concepts of greenhouse gases emissions and its impact on climate change and summarizes the main objectives of the strategic EU energy packages and of the Paris agreement. It then focuses on methodologies for estimating the impact of renewable energies on greenhouse gases emissions reduction and reviews the reported EU related achievements. It also proposes a classification of EU countries in terms of Tapio decoupling states by analyzing and classifying the countries emissions intensities and its variation for a considered time period and analyzes the impact renewable energies had in that greenhouse gases emissions variations, in relation with other possibly relevant factors. The chapter ends with a summary of the expected evolution of renewable energies in the EU, and with the final conclusions.

Abstract
The concept of urban mobility development needs to be somehow reconsidered towards planning and implementing transports in a more sustainable, inclusive and integrated manner. It urges to monitor and evaluate the sustainable development of the cities based on a triple bottom line dimension - economic, social and environmental; as well as on the main indicators, including the ones regarding the cities context and particularities. Hence, the definition of sustainability indicators and the associated index is a major tool towards gaining higher visibility of the current state of mobility and to establish goals and milestones to attain the desired sustainability. According to the Viana do Castelo case study, a description of the city and of the existents transports is presented, and Sustainable Urban Mobility Plan guidelines are also proposed. In this paper, a set of sustainability indicators are defined with balanced distribution by the sustainability dimensions, according to the benchmarking analysis and the Viana do Castelo' characteristics - including the ones regarding the historic city center. These sustainability indicators enable the development of an evolutive sustainable profile, provide knowledge to the redesign of sustainable urban policies in the Viana do Castelo city and in the Alto Minho Region context.

Abstract
Exposing electric vehicles (EV) to extreme temperatures limits its performance and charging. For the foreseen adoption of EVs, it is not only important to study the technology behind it, but also the environment it will be inserted into. In Europe, temperatures ranging from -30°C to +40°C are frequently observed and the impacts on batteries are well-known. However, the impact on the grid due to the performance of fast-chargers, under such conditions, also requires analysis, as it impacts both on the infrastructure's dimensioning and design. In this study, six different fast-chargers were analysed while charging a full battery EV, under four temperature levels (-25 °C, -15 °C, +20 °C, and +40 °C). The current total harmonic distortion, power factor, standby power, and unbalance were registered. Results show that the current total harmonic distortion (THDI) tended to increase at lower temperatures. The standby consumption showed no trend, with results ranging from 210 VA to 1650 VA. Three out of six chargers lost interoperability at -25 °C. Such non-linear loads, present high harmonic distortion, and, hence, low power factor. The temperature at which the vehicle's battery charges is crucial to the current it withdraws, thereby, influencing the charger's performance.