Abstract
This paper explores the application of Deep Learning techniques to forecast electricity market prices. Three Deep Learning (DL) techniques are tested: Dense Neural Networks (DNN), Long Short-Term Memory Networks (LSTM) and Convolutional Neural Networks (CNN); and two non-DL techniques: Multiple Linear Regression and Gradient Boosting (GB). First, this work compares the forecast skill of all techniques for electricity price forecasting. The results analysis showed that CNN consistently remained among the best performers when predicting the most unusual periods such as the Covid19 pandemic one. The second study evaluates the potential application of CNN for automatic feature extraction over a dataset composed by multiple explanatory variables of different types, overcoming part of the feature selection challenges. The results showed that CNNs can be used to reduce the need for a variable selection phase.

Abstract
This paper presents a methodology to estimate flexibility existing on TSO-DSO borderline, for the cases where multiple TSO-DSO connections exist (meshed grids). To do so, the work conducted exploits previous developments regarding flexibility representation through the adoption of active and reactive power flexibility maps and extends the concept for the cases where multiple TSO-DSO connection exists, using data-driven approach to determine the equivalent impedance between TSO nodes, preserving the anonymity regarding sensitive grid information, such as the topology. This paper also provides numerical validation followed by real-world demonstration of the methodology proposed.

Abstract
Hydrogen is regarded as a flexible energy carrier with multiple applications across several sectors. For instance, it can be used in industrial processes, transports, heating, and electrical power generation. Green hydrogen, produced from renewable sources, can have a crucial role in the pathway towards global decarbonization. However, the success of green hydrogen production ultimately depends on its economic sustainability. In this context, this work evaluates the economic performance of a hydrogen power plant participating in the electricity market and supplying multiple hydrogen consumers. The analysis includes technical and economical details of the main components of the hydrogen power plant. Its operation is simulated using six different scenarios, which admit the production of either grey or green hydrogen. The scenarios used for the analysis include data from the Iberian electricity market for the Portuguese hub. An important conclusion is that the combination of multiple services in a hydrogen power plant has a positive effect on its economic performance. However, as of today, consumers who would wish to acquire green hydrogen would have to be willing to pay higher prices to compensate for the shorter periods of operation of hydrogen power plants and for their intrinsic losses. Nonetheless, an increase in green hydrogen demand based on a greater environmental awareness can lead to the need to not only build more of these facilities, but also to integrate more services into them. This could promote the investment in hydrogen-related technologies and result in changes in capital and operating costs of key components of these plants, which are necessary to bring down production costs.

Abstract
The rising potential for battery energy storage systems (BESS) to generate revenue in a market environment is addressed in this work, where a tool based on neural network predictions is proposed. The tool's main objective is predicting, based on historical data, the most lucrative out of three established bidding approaches for the participation of a BESS in the day-ahead energy market and thus aid the strategic bidding process of the BESS operator. Each of these bidding strategies reflects BESS's operator approach concerning bidding frequency and the tolerated risk of loss of profit from having its bids rejected, leading to the development of a conservative (strategy A), an aggressive (strategy B), and a moderate strategy (strategy C). A case study was then used to test the tool for a full year allowing to ascertain the assertiveness of this tool in predicting the best strategy, which for this case was above 88%.

Abstract
The decarbonisation of the building sector is crucial for Portugal's goal of achieving economy-wide carbon neutrality by 2050. To mobilize communities towards energy efficiency measures, it is important to understand the primary drivers and barriers that must be overcome through policymaking. This paper aims to review existing Energy Policies and Actions (EPA) in Portugal and assess their effectiveness in improving Energy Efficiency (EE) and reducing CO2 emissions in the building sector. The Local Energy Planning Assistant (LEPA) tool was used to model, test, validate and compare the implementation of current and alternative EPAs in the North of Portugal, including the national EE plan. The results indicate that electrification of heating and cooling, EE measures, and the proliferation of Renewable Energy Sources (RES) are crucial for achieving climate neutrality. The study found that the modelling of alternative EPAs can be improved to reduce investment costs and increase Greenhouse Gas (GHG) emissions reduction. Among the alternatives assessed, the proposed one (Alternative 4) presents the best returns on investment in terms of cost savings and emissions reduction. It allows for 52% investment cost savings in the residential sector and 13% in the service sector when compared to the current national roadmap to carbon neutrality (Alternative 2). The estimated emission reduction in 2050 for Alternative 4 is 0.64% for the residential sector and 3.2% for the service sector when compared to Alternative 2.

Abstract
Energy communities have been designed to empower consumers while maximizing the self-consumption of local renewable energy sources (RESs). Their presence in distribution systems can result in strong modifications in the operation and management of such systems, moving from a centralized operation to a distributed one. In this scope, this work proposes a distributed community-based local energy market that aims at minimizing the costs of each community member, accounting for the technical network constraints. The alternating direction method of multipliers (ADMM) is adopted to distribute the market, and preserve, as much as possible, the privacy of the prosumers' assets, production, and demand. The proposed method is tested on a 10-bus medium voltage radial distribution network, in which each node contains a large prosumer, and the relaxed branch flow model is adopted to model the optimization problem. The market framework is proposed and modeled in a centralized and distributed fashion. Market clearing on a day-ahead basis is carried out taking into account actual energy exchanges, as generation from renewable sources is uncertain. The comparison between the centralized and distributed ADMM approach shows an 0.098% error for the nodes' voltages. The integrated OPF in the community-based market is a computational burden that increases the resolution of the market dispatch problem by about eight times the computation time, from 200.7 s (without OPF) to 1670.2 s. An important conclusion is that the proposed market structure guarantees that P2P exchanges avoid the violation of the network constraints, and ensures that community agents' can still benefit from the community-based architecture advantages.