We propose a new unsupervised anomaly detection method based on the sliced-Wasserstein distance for training data selection in machine learning approaches. Our filtering technique is interesting for decision-making pipelines deploying machine learning models in critical sectors, e.g., electric power systems, as it offers a conservative data selection and an optimal transport interpretation. To ensure the scalability of our method, we provide two efficient approximations. The first approximation processes reduced-cardinality representations of the datasets concurrently. The second method utilizes a computationally lightweight Euclidian distance approximation. Additionally, we focus our analysis on virtual power plants as we open the first dataset showcasing localized critical peak rebate demand response of power systems in a northern climate. We present the filtering patterns of our method on synthetic datasets and numerically benchmark our method for training data selection. Finally, we employ our method as part of a first load forecasting benchmark for our open-source dataset.

The optimal power flow (OPF) problem focuses on the operational efficiency of electric power systems. Modern grids include a variety of devices that are often omitted in traditional OPF formulations, namely, different types of generators, transformers, or power electronics-based devices. The modified and augmented nodal analysis (MANA) extends the traditional nodal analysis by expressing circuit equations in a generic sparse matrix representation. The MANA approach can seamlessly accommodate constraints from various types of devices commonly encountered in modern networks. This, in turn, allows their straightforward inclusion as constraints in OPF by modelling them through MANA using their current and voltage equations. This work proposes a new OPF formulation based on MANA and the corresponding power flow constraints, which we refer to as MANA-OPF. The non-convex MANA-OPF is solved using a nonlinear solver, namely, IPOPT in Julia. The formulation is tested on several test cases. The results are compared to a standard approach used by PowerModels.

Model predictive control (MPC) has been shown to significantly improve the energy efficiency of buildings while maintaining thermal comfort. Data-driven approaches like neural networks can facilitate system modelling. However, such approaches are generally nonconvex and result in computationally intractable optimization problems. In this work, we design a readily implementable energy management method for small commercial buildings. We then leverage our approach to formulate a real-time demand bidding strategy. We propose a data-driven and mixed-integer convex MPC which is solved via derivative-free optimization given a limited computational time of 5 minutes to respect operational constraints. We consider rooftop unit heating, ventilation, and air conditioning systems with discrete controls to accurately model the operation of most commercial buildings. Our approach uses an input convex recurrent neural network to model the thermal dynamics. We apply our approach to several demand response settings, including a demand bidding a time-of-use, and a critical peak rebate program. Controller performance is evaluated on a state-of-the-art building simulation.

Arctic regions, such as northern Canada, face significant challenges in achieving consistent connectivity and low-latency computing services due to the sparse coverage of Low Earth Orbit (LEO) satellites. To enhance service reliability in remote areas, this paper proposes a hybrid satellite architecture for task offloading that combines Medium Earth Orbit (MEO) and LEO satellites. We develop an optimization framework to maximize task offloading admission rate while balancing the energy consumption and delay requirements. Accounting for satellite visibility and limited computing resources, our approach integrates dynamic path selection with frequency and computational resource allocation. Because the formulated problem is NP-hard, we reformulate it into a mixed-integer convex form using disjunctive constraints and convex relaxation techniques, enabling efficient use of off-the-shelf optimization solvers. Simulation results show that, compared to a standalone LEO network, the proposed hybrid LEO-MEO architecture improves the task admission rate by 15% and reduces the average delay by 12%. These findings highlight the architecture’s potential to enhance connectivity and user experience in remote Arctic areas.

The increasing demand for data usage in wireless communications requires using wider bands in the spectrum, especially for backhaul links. Yet, allocations in the spectrum for non-communication systems inhibit merging bands to achieve wider bandwidth. To overcome this issue, spectrum-sharing or opportunistic spectrum utilization by secondary users stands out as a promising solution. However, both approaches must minimize interference to primary users. Therefore, spectrum sensing becomes vital for such opportunistic usage, ensuring the proper operation of the primary users. Although this problem has been investigated for two-dimensional networks, unmanned aerial vehicle (UAV) networks need different approaches concerning three-dimensional space, its challenges, and opportunities. For this purpose, we propose a federated learning (FL)-based method for spectrum sensing in UAV networks to account for their distributed nature and limited computational capacity. FL enables local training without sharing raw data while guaranteeing the privacy of local users, lowering communication overhead, and increasing data diversity. Furthermore, we develop a federated aggregation method, namely FedSNR, that considers the signal-to-noise ratio observed by UAVs to acquire a global model. The numerical results show that the proposed architecture and the aggregation method outperform traditional methods.

This paper presents state-space models for both doubly-fed induction generator (DFIG) and full-scale converter (FSC)-based wind parks (WPs) that can be used to investigate the WP control interaction (CI) problems. The presented models are tested on a series capacitor compensated WP benchmark which exhibits different type instability phenomenon for DFIG and FSC-based WP connection scenarios. The obtained results are validated through simulations using EMTP®. The presented models can be used to develop a state-space analysis (SSA) tool for large-scale multi WP systems to identify the potential WP related instability conditions.