The ability to accurately forecast power generation from renewable sources is nowadays recognised as a fundamental skill to improve the operation of power systems. Despite the general interest of the power community in this topic, it is not always simple to compare different forecasting methodologies, and infer the impact of single components in providing accurate predictions. In this paper we extensively compare simple forecasting methodologies with more sophisticated ones over 32 photovoltaic plants of different size and technology over a whole year. Also, we try to evaluate the impact of weather forecasts on the prediction of PV power generation.

Small target detection is still a challenging task, especially when looking at fast and accurate solutions for mobile or edge applications. In this work, we present YOLO-S, a simple, fast, and efficient network. It exploits a small feature extractor, as well as skip connection, via both bypass and concatenation, and a reshape-passthrough layer to promote feature reuse across network and combine low-level positional information with more meaningful high-level information. Performances are evaluated on AIRES, a novel dataset acquired in Europe, and VEDAI, benchmarking the proposed YOLO-S architecture with four baselines. We also demonstrate that a transitional learning task over a combined dataset based on DOTAv2 and VEDAI can enhance the overall accuracy with respect to more general features transferred from COCO data. YOLO-S is from 25% to 50% faster than YOLOv3 and only 15–25% slower than Tiny-YOLOv3, outperforming also YOLOv3 by a 15% in terms of accuracy (mAP) on the VEDAI dataset. Simulations on SARD dataset also prove its suitability for search and rescue operations. In addition, YOLO-S has roughly 90% of Tiny-YOLOv3’s parameters and one half FLOPs of YOLOv3, making possible the deployment for low-power industrial applications.

The computational cost of topology optimization based on binary particle swarm optimization is greatly reduced by the use of Deep Neural Networks (DNN). A first Convolutional Neural Network (CNN) is trained with data coming from Finite Element Analysis (FEA) with the aim of correctly estimating the output quantity (a motor torque in the proposed case study). A second CNN is trained to give as output the boundary conditions (BC, expressed in terms of fields or potentials) to be used as BC of a reduced Finite Element Method (FEM) model, created in order to still be able to give the correct value of the output quantity. In the optimization phase, the torque properties are evaluated by the trained CNN, and only a reduced percentage of cases are re-evaluated by either the full FEM model or the reduced FEM model. The overall computational time of the optimization procedure is significantly reduced.

Predictive Maintenance, Prognostics and Reliability Centered Maintenance approach are becoming more and more important in the railway sector to reduce costs of operation and to increase reliability and safety. In fact, these are fundamental to optimize the maintenance process, to define new measures and algorithms which locate faults, to monitor health conditions of subsystems and to estimate residual life of components. In some cases it's possible to use existing sensors and existing processing hardware to extract new information from the existing available data. It's clear that this is usually the best option because the benefit can be achieved with little or no cost at all. This paper describes the result of a study performed with the aim of detecting arcing events without the need of additional equipment mounted on board the train. A set of data relative to voltage and current collected on high speed trains along with a set of measurements coming from photosensors are available. The data are processed by the use of an advanced classification technique, Support Vector Machines, with the aim of extracting important information such as the time coordinate related to anomalies in the overhead contact line and the status of the pantograph contact strip.

This paper presents a theoretical and experimental analysis on the application of power-line communication (PLC) on a cruise ship. The authors have developed an accurate model of the power grid of a ship when it is used as a PLC channel. The model is developed based on a theoretical approach and validated by a thorough measurement campaign. The accuracy of the model is addressed by a comparison between simulation results and measured data, and its use gives an insight into the performance of the power network to be used as PLC channel.

In this work a topology optimization procedure is proposed and applied to the TEAM 25 problem, i.e. a model of a die press with electromagnet for orientation of magnetic powder. The shape of the press is described as a free discretized profile, and its relation to the flux density in the cavity is simulated by Finite Element Analysis (FEA) and learned by a Deep Neural Network (DNN) model. The DNN is used as a surrogate model for optimization, aiming to obtain a desired flux density distribution in the cavity. Results are promising, as better accuracy is obtained with respect to full FEA-based optimization approach with reduced time cost. Once trained, surrogate model can be used to efficiently solve a whole family of problems where a different target field distribution is defined.