Abstract
Although electricity is a clean and relatively safe form of energy when it is used, the generation and transmission of electricity have severe effects on the environment. An alternative to diminish the polluting emissions released by the generating units is the Emission Constrained Economic Dispatch (ECED). This is an optimization problem where the total fuel cost is minimized while treating emissions as a constraint with a pre-specified limit. Usually, the fuel cost and emission functions of the generating units must be experimentally derived, introducing then uncertainties in the obtained models. However, these uncertainties are often neglected and the ECED problem is solved considering the coefficients of the functions involved as exact (totally known) values. In this investigation we analyzed the effect of the uncertainties associated to the experimental derivation of the input–output curves of thermal power plants. Particularly, when polynomial models are fitted through multiple linear regression, we proposed an approach that, based on the respectively prediction intervals, can provide solutions immunized, in some sense, against variability in the coefficients estimates. We tested the proposed approach in a real system from the Chilean electrical power network. For the analyzed system we noted that, when uncertainties are not considered, the deterministic optimal solutions can be environmentally infeasible in some scenarios; whereas solutions obtained through the proposed approach, can significantly diminish the risk of environmental violations. The robustness of the prediction interval-based solutions was obtained with a negligible increase of the total fuel cost in all the cases studied.

Abstract

Abstract
Covid-19 posed several challenges to all organisations in general and to social solidarity cooperatives in particular. However, the challenges faced by these cooperatives have unique features arising from their special characteristics compared to other types of cooperatives. Therefore it is vital to study these challenges and the impacts of covid-19. This study has as main goal to understand those challenges and their impact. An exploratory study was undertaken by applying 11 interviews to 11 social solidarity cooperatives. The cooperatives were chosen to be heterogeneous among the existent cooperatives in Portugal. This study corresponds to the first phase of a project that is still underway. This article presents the main results of the content analysis of the data collected from the interviews. Data show cooperatives could promptly adapt and continue their mission under pressure from the pandemic despite the first difficulties encountered in a new and unknown situation, showing a capacity to adapt and serve their members. However, these members were also submitted to several increasing and new challenges. The adaptations were possible due to legal changes in the work organisation law, from layoff to telework, government support involving financial programs, VAT, and other tax relaxation, as well as due to human resources reorganisation and the cooperatives' staff positive attitude towards the difficulties (both leaders and general workers). Differences between the social solidarity cooperatives under study concerning digital technologies showed that those already having some infrastructure had minor adapting difficulties.

Abstract
Accurate ultra-short-term PV power forecasting is essential for the power system with a high proportion of renewable energy integration, which can provide power fluctuation information hours ahead and help to mitigate the interference of the random PV power output. Most of the PV power forecasting methods mainly focus on employing local ground-based observation data, ignoring the spatial and temporal distribution and correlation characteristics of solar energy and meteorological impact factors. Therefore, a novel ultra-short-term PV power forecasting method based on the satellite image data is proposed in this paper, which combines the spatio-temporal correlation between multiple plants with power and cloud information. The associated neighboring plant is first selected by spatial-temporal cross-correla-tion analysis. Then the global distribution information of the cloud is extracted from satellite images as additional inputs with other general meteorological and power inputs to train the forecasting model. The proposed method is compared with several benchmark methods without considering the information of neighboring plants. Results show that the proposed method outperforms the benchmark methods and achieves a higher accuracy at 4.73%, 10.54%, and 4.88%, 11.04% for two target PV plants on a four-month validation dataset, in terms of root mean squared error and mean absolute error value, respectively.

Abstract
This paper reports the research and design of a foldable disaster shelter for people left homeless due to natural disasters, by a multinational team composed of six students, from six different countries. The team was enrolled in the European Project Semester (EPS), a project-based capstone programme offered by Instituto Superior de Engenharia do Porto (ISEP), to students who have completed at least two years of undergraduate studies. The main objective of the project was to design, simulate and test an ethics and sustainability driven foldable shelter. This goal was pursued by conducting a series of studies to derive the solution requirements, involving a survey on shelter concepts and solutions, a review on worldwide natural disasters, as well as an analysis of the shelter market. The latter led to the definition of a business plan, a marketing strategy, a logo and a brand name. The solution comes with a Web application to help rescue organisations to follow the scheduled maintenance plan and keep track of the deployed units.

Abstract
Deep Learning achieves state-of-the-art results in many domains, yet its black-box nature limits its application to real-world contexts. An intuitive way to improve the interpretability of Deep Learning models is by explaining their decisions with similar cases. However, case-based explanations cannot be used in contexts where the data exposes personal identity, as they may compromise the privacy of individuals. In this work, we identify the main limitations and challenges in the anonymization of case-based explanations of image data through a survey on case-based interpretability and image anonymization methods. We empirically analyze the anonymization methods in regards to their capacity to remove personally identifiable information while preserving relevant semantic properties of the data. Through this analysis, we conclude that most privacy-preserving methods are not sufficiently good to be applied to case-based explanations. To promote research on this topic, we formalize the privacy protection of visual case-based explanations as a multi-objective problem to preserve privacy, intelligibility, and relevant explanatory evidence regarding a predictive task. We empirically verify the potential of interpretability saliency maps as qualitative evaluation tools for anonymization. Finally, we identify and propose new lines of research to guide future work in the generation of privacy-preserving case-based explanations.