Amedeo Buonanno

Foundation models for time series forecasting have recently been applied to energy prediction tasks, where they can produce accurate forecasts without task-specific training. This study investigates the impact of two types of covariates, meteorological variables and calendar-based day type indicators, on the forecasting performance of Chronos-2, a state-of-the-art foundation model, in building energy consumption prediction. Using real-world monitoring data from two non-residential buildings at the ENEA Research Centre in Portici, Italy, we systematically evaluate seven configurations combining past and future covariates across multiple observation window lengths (7–28 days). Future meteorological covariates are derived from historical weather forecasts rather than observed weather data, ensuring that the evaluation reflects realistic operational forecasting conditions. The results show that incorporating day type indicators as both past and future covariates consistently delivers the highest forecasting accuracy, reducing CV-RMSE from 14.58% for the covariate-free baseline to 10.41% with a 28-day observation window. A day-stratified analysis further reveals that these improvements are concentrated on regime transition days, for which recent load history alone provides limited information about the operating conditions of the day being forecast. By contrast, meteorological variables, whether obtained from weather forecasts or historical observations, yield only marginal performance gains, suggesting that calendar-driven operational schedules are the primary determinants of energy demand in the buildings considered. These findings provide practical guidance for deploying foundation models in real-world energy building management systems and show that covariate selection is a key determinant of forecasting performance.

This study addresses the challenge of access point (AP) and user equipment (UE) association in cell-free massive MIMO networks. It introduces a deep learning algorithm based on Bidirectional Long Short-Term Memory cells (a specific type of Recurrent Neural Network) and a hybrid probabilistic methodology for weight updating. This approach enhances scalability by adapting to variations in the number of UEs without requiring retraining. In addition, the study proposes a novel master-centric methodology for managing the AP-UE association process, which helps improve scalability not only with respect to the number of UEs, but also to that of APs. Furthermore, a variant of the proposed AP-UE algorithm ensures robustness against pilot contamination effects, a critical issue arising from pilot reuse in channel estimation. Extensive numerical results validate the effectiveness and adaptability of the proposed methods, demonstrating clear advantages over widely used heuristic alternatives.

This paper provides a comprehensive analysis of Frequency Modulated Orthogonal Frequency Division Multiplexing (FM-OFDM), a novel modulation technique exhibiting good levels of robustness when employed on wireless communication links in high-mobility environments. A novel transceiver receiver design that eliminates the need for phase unwrapping, thereby reducing computational complexity, is proposed. Analytical performance of the modulation is assessed through mathematical derivation of closed-form expressions for the signal-to-noise ratio (SNR) per subcarrier. Such expressions provide in-depth understanding of both ideal and more realistic communication scenarios. Additionally, the paper also contains analytical derivations that permit to evaluate the power spectral density and bandwidth characteristics of the FM-OFDM modulation. Numerical results show the effectiveness of the FM-OFDM waveform in environments affected by large Doppler shifts, as well as the remarkable performance level of the newly proposed low-complexity detector.

This study addresses the challenge of access point (AP) and user equipment (UE) association in cell-free massive MIMO networks. It introduces a deep learning algorithm leveraging Bidirectional Long Short-Term Memory cells and a hybrid probabilistic methodology for weight updating. This approach enhances scalability by adapting to variations in the number of UEs without requiring retraining. Additionally, the study presents a training methodology that improves scalability not only with respect to the number of UEs but also to the number of APs. Furthermore, a variant of the proposed AP-UE algorithm ensures robustness against pilot contamination effects, a critical issue arising from pilot reuse in channel estimation. Extensive numerical results validate the effectiveness and adaptability of the proposed methods, demonstrating their superiority over widely used heuristic alternatives.

The combination of different energy vectors like electrical energy, hydrogen, methane, and water is a crucial aspect to deal with in integrated local energy communities (ILECs). The ILEC stands for a set of active energy users that maximise benefits and minimise costs using optimisation procedures in producing and sharing energy. In particular, the proper management of different energy vectors is fundamental for achieving the best operating conditions of ILECs in terms of both energy and economic perspectives. To this end, different solutions have been developed, including advanced control and monitoring systems, distributed energy resources, and storage. Energy management planning software plays a pivotal role in developing ILECs in terms of performance evaluation and optimisation within a multi-carrier concept. In this paper, the state-of-the-art of ILECs is further enhanced by providing important details on the critical aspects related to the overall value chain for constituting an ILEC (e.g., conceptualisation, connecting technologies, barriers/limitations, control, and monitoring systems, and modelling tools for planning phases). By providing a clear understanding of the technical solutions and energy planning software, this paper can support the energy system transition towards cleaner systems by identifying the most suitable solutions and fostering the advancement of ILECs.

This paper addresses the problem of joint multiplexing of enhanced Mobile Broadband (eMBB) and massive Machine-Type Communications (mMTC) traffic in the same uplink time-frequency RG. Given the challenge posed by a potentially large number of users, it is essential to focus on a multiple access strategy that leverages artificial intelligence to adapt to specific channel conditions. An mMTC agent is developed through a Deep Reinforcement Learning (DRL) methodology for generating grant-free frequency hopping traffic in a decentralized manner, assuming the presence of underlying eMBB traffic dynamics. Within this DRL framework, a methodical comparison between two possible deep neural networks is conducted, using different generative models employed to ascertain their intrinsic capabilities in various application scenarios. The analysis conducted reveals that the Long Short-Term Memory network is particularly suitable for the required task, demonstrating a robustness that is consistently very close to potential upper-bounds, despite the latter requiring complete knowledge of the underlying statistics.