Abstract
Reliability analysis of large power networks requires accurate aggregate models of low voltage (LV) networks to allow for reasonable calculation complexity and to prevent long computational times. However, commonly used lumped load models neglect the differences in spatial distribution of demand, type of phase-connection of served customers and implemented protection system components (e.g., single-pole vs three-pole). This paper proposes a novel use of state enumeration (SE) and Monte Carlo simulation (MCS) techniques to formulate more accurate LV network reliability equivalents. The combined SE and MCS method is illustrated using a generic suburban LV test network, which is realistically represented by a reduced number of system states. This approach allows for a much faster and more accurate reliability assessments, where further reduction of system states results in a single-component equivalent reliability model with the same unavailability as the original LV network. Both mean values and probability distributions of standard reliability indices are calculated, where errors associated with the use of single-line models, as opposed to more detailed three-phase models, are quantified.

Abstract
A common problem in distribution planning is the scarcity of historic data (training examples) relative to the number of variables, meaning that most data-driven techniques cannot be applied in such situations, due to the risk of overfitting. Thus, the suitable regression techniques are restrained to efficient models, preferably with embedded regularization features. This article compares three of these techniques: LASSO, Bayesian and CMLR (Conditioned multi-linear regression - a new approach developed within the scope of a project with a distribution company). The results showed that each technique has its own advantages and limitations. The Bayesian regression has the main advantage of providing inherent confidence intervals. The LASSO is a very economic and efficient regression tool. The CMLR is versatile and provided the best performance.A common problem in distribution planning is the scarcity of historic data (training examples) relative to the number of variables, meaning that most data-driven techniques cannot be applied in such situations, due to the risk of overfitting. Thus, the suitable regression techniques are restrained to efficient models, preferably with embedded regularization features. This article compares three of these techniques: LASSO, Bayesian and CMLR (Conditioned multi-linear regression - a new approach developed within the scope of a project with a distribution company). The results showed that each technique has its own advantages and limitations. The Bayesian regression has the main advantage of providing inherent confidence intervals. The LASSO is a very economic and efficient regression tool. The CMLR is versatile and provided the best performance.

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%.