Abstract

Abstract
Electricity demand may vary significantly and consequently the generation side must be adapted to fully supply it. However, the increased penetration of variable renewable energy sources is changing the game by leading to an increase need of load response and load flexibility to face these changes from the generation side. Flexibility is highly related to the viability of Demand Response actions that can allow the participation of loads from buildings, clusters of communities, industry in market-driven energy services. Policymakers and energy stakeholders are beginning to prepare for a reality in which many consumers are also producers (prosumers) and operate with a significantly decentralized electricity grid. Also, the increased use of information and communication technologies is creating new opportunities for smarter control and load management schemes, interconnecting multiple demand-side stakeholders, where prosumers can leverage the potential for energy flexibility in demand-response programs. This chapter presents an overview of strategies to enable end-user participation in energy services, including building optimization schemes that provide load flexibility for the grid, as single users or as aggregated communities.

Abstract
Object identification, such as tree trunk detection, is fundamental for forest robotics. Intelligent vision systems are of paramount importance in order to improve robotic perception, thus enhancing the autonomy of forest robots. To that purpose, this paper presents three contributions: an open dataset of 5325 annotated forest images; a tree trunk detection Edge AI benchmark between 13 deep learning models evaluated on four edge-devices (CPU, TPU, GPU and VPU); and a tree trunk mapping experiment using an OAK-D as a sensing device. The results showed that YOLOR was the most reliable trunk detector, achieving a maximum F1 score around 90% while maintaining high scores for different confidence levels; in terms of inference time, YOLOv4 Tiny was the fastest model, attaining 1.93 ms on the GPU. YOLOv7 Tiny presented the best trade-off between detection accuracy and speed, with average inference times under 4 ms on the GPU considering different input resolutions and at the same time achieving an F1 score similar to YOLOR. This work will enable the development of advanced artificial vision systems for robotics in forestry monitoring operations.

Abstract
The emergence of Industry 4.0 is making production systems more flexible and also more dynamic. In these settings, schedules often need to be adapted in real-time by dispatching rules. Although substantial progress was made until the '90s, the performance of these rules is still rather limited. The machine learning literature is developing a variety of methods to improve them. However, the resulting rules are difficult to interpret and do not generalise well for a wide range of settings. This paper is the first major attempt at combining machine learning with domain problem reasoning for scheduling. The idea consists of using the insights obtained with the latter to guide the empirical search of the former. We hypothesise that this guided empirical learning process should result in effective and interpretable dispatching rules that generalise well to different scenarios. We test our approach in the classical dynamic job shop scheduling problem minimising tardiness, one of the most well-studied scheduling problems. The simulation experiments include a wide spectrum of scenarios for the first time, from highly loose to tight due dates and from low utilisation conditions to severely congested shops. Nonetheless, results show that our approach can find new state-of-the-art rules, which significantly outperform the existing literature in the vast majority of settings. Overall, the average improvement over the best combination of benchmark rules is 19%. Moreover, the rules are compact, interpretable, and generalise well to extreme, unseen scenarios. Therefore, we believe that this methodology could be a new paradigm for applying machine learning to dynamic optimisation problems.

Abstract
This work focuses on detection of upper gas-trointestinal (GI) landmarks, which are important anatomical areas of the upper GI tract digestive system that should be photodocumented during endoscopy to guarantee a complete examination. The aim of this work consisted in testing new automatic algorithms, specifically based on convolutional neural network (CNN) systems, able to detect upper GI landmarks, that can help to avoid the presence of blind spots during esophagogastroduodenoscopy. We tested pre-trained CNN architectures, such as the ResNet-50 and VGG-16, in conjunction with different training approaches, including the use of class weights, batch normalization, dropout, and data augmentation. The ResNet-50 model trained with class weights was the best performing CNN, achieving an accuracy of 71.79% and a Mathews Correlation Coefficient (MCC) of 65.06%. The combination of supervised and unsupervised learning was also explored to increase classification performance. In particular, convolutional autoencoder architectures trained with unlabeled GI images were used to extract representative features. Such features were then concatenated with those extracted by the pre-trained ResNet-50 architecture. This approach achieved a classification accuracy of 72.45% and an MCC of 65.08%. Clinical relevance - Esophagogastroduodenoscopy (EGD) photodocumentation is essential to guarantee that all areas of the upper GI system are examined avoiding blind spots. This work has the objective to help the EGD photodocumentation monitorization by testing new CNN-based systems able to detect EGD landmarks.

Abstract
To continue to make successful progress towards the achievement of net zero emissions by 2050, a significant number of new facilities based on renewable technologies must continue to be deployed at large scale. However, the integration of large capacities of renewable generation sources into power systems leads to a series of challenges that must be urgently addressed. On the one hand, the intermittent character of renewable resources may lead to imbalances between generation and demand curves, and on the other hand, transmission and distribution system operators will have to carefully consider the impact of reduced power system inertia due to the increase in the number of renewable power plants. Under this framework, stricter technical requirements will be demanded to new power plants that will be integrated into the grid to guarantee quality of electricity supply. These requirements are included within increasingly modern and up-to-date network connection-or grid-codes. Thus, grid codes have a significant role to play in the years to come towards the transition of a more sustainable future, and therefore this paper presents an overview of two grid codes for connecting new generation units across Europe, focusing on the current situation of Iberia. A special emphasis is given on the detailing of certain grid code requirements based on a comparison between the Portuguese and the Spanish grid codes, together with few highlights on the operational procedures for connecting new generation units on both regions. © 2022, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.