Abstract
Forecasting energy consumption models allow for improvements in building performance and reduce energy consumption. Energy efficiency has become a pressing concern in recent years due to the increasing energy demand and concerns over climate change. This paper addresses the energy consumption forecast as a crucial ingredient in the technology to optimize building system operations and identifies energy efficiency upgrades. The work proposes a modified multi-head transformer model focused on multi-variable time series through a learnable weighting feature attention matrix to combine all input variables and forecast building energy consumption properly. The proposed multivariate transformer-based model is compared with two other recurrent neural network models, showing a robust performance while exhibiting a lower mean absolute percentage error. Overall, this paper highlights the superior performance of the modified transformer-based model for the energy consumption forecast in a multivariate step, allowing it to be incorporated in future forecasting tasks, allowing for the tracing of future energy consumption scenarios according to the current building usage, playing a significant role in creating a more sustainable and energy-efficient building usage.

Abstract
This paper presents an innovative digital platform for managing energy communities with self-consumption and energy trading in a local electricity market. Its architecture is based on micro-services, such as the energy transaction service, the settlement service to compute the financial compensations among community members for the energy transacted, or a resource sizing service. This approach enables the platform to be more efficient and scalable, making easier to incorporate new functionalities while maintaining a secure community and energy transactions management. The transactions and settlement procedures, adapted to the Portuguese regulation, are described, and the results of the platform operating a post-delivery pool market are presented and analyzed. This paper contributes to the understanding and improvement of renewable energy communities' business models and management, offering insights for policymakers, researchers, and practitioners in the field.

Abstract
The resource-constrained project scheduling problem (RCPSP) is a well-known scheduling problem that has attracted attention since several decades. Despite the rapid progress of exact and (meta-)heuristic procedures, the problem can still not be solved to optimality for many problem instances of relatively small size. Due to the known complexity, many researchers have proposed fast and efficient meta-heuristic solution procedures that can solve the problem to near optimality. Despite the excellent results obtained in the last decades, little is known why some heuristics perform better than others. However, if researchers better understood why some meta-heuristic procedures generate good solutions for some project instances while still falling short for others, this could lead to insights to improve these meta-heuristics, ultimately leading to stronger algorithms and better overall solution quality. In this study, a new hardness indicator is proposed to measure the difficulty of providing near-optimal solutions for meta-heuristic procedures. The new indicator is based on a new concept that uses the o-distance metric to describe the solution space of the problem instance, and relies on current knowledge for lower and upper bound calculations for problem instances from five known datasets in the literature. This new indicator, which will be called the o -D indicator, will be used not only to measure the hardness of existing project datasets, but also to generate a new benchmark dataset that can be used for future research purposes. The new dataset contains project instances with different values for the o -D indicator, and it will be shown that the value of the o-distance metric actually describes the difficulty of the project instances through two fast and efficient meta-heuristic procedures from the literature.

Abstract
In this work, the prediction of a time series is formulated as a gaussian process regression, for different levels of noise. The gaussian regressor is translated into lower rank Dynamic Mode Decomposition methods that use kernels (K-DMD) - Kernel regression and Least Squares Support Vector Machines. The presented unified approach delivers an algorithm where the optimisation of the marginal likelihood function can be used to find the parameters of the kernel regression. The viability of the procedure is demonstrated on a chaotic series, with quite good adjustment results being obtained. Copyright (c) 2023 The Authors.

Abstract
Sectorization problems, also known as districting or territory design, deal with grouping a set of previously defined basic units, such as points or small geographical areas, into a fixed number of sectors or responsibility areas. Usually, there are multiple criteria to be satisfied regarding the geographic characteristics of the territory or the planning purposes. This work addresses a case study of parcel delivery services in the region of Porto, Portugal. Using knowledge about the daily demand in each basic unit (7-digit postal code), the authors analysed data and used it to simulate dynamically new daily demands according to the relative frequency of service in each basic unit and the statistical distribution of the number of parcels to be delivered in each basic unit. The sectorization of the postal codes is solved independently considering two objectives (equilibrium and compactness) using Non-dominated Sorting Genetic Algorithm-II (NSGA-II) implemented in Python.

Abstract
White Light Interferometry, known for its absolute measurement capability and high precision, had its greatest scientific impact towards the end of the 20th century. In this work, it was assembled and characterized a fibre Mach-Zehnder interferometer (MZI) as an interrogator and a fibre Fabry-Perot interferometer (FPI) as a displacement sensor. A measurement bandwidth between 65 µm and 95 µm was obtained for FPI cavities close to 2.35 mm, at sampling frequencies between 600 Hz and 1500 Hz. Additionally, a resonant frequency at 550 Hz was achieved, allowing for an interrogation band higher than 135 µm. It was also determined a minimum absolute resolution of ± 66 nm, corresponding to a relative resolution of ± 9.4×10-4 in relation to the total band.