No abstract

The current flexibility of the energy market requires operating steam turbines that have challenging operation requirements such as variable steam conditions and higher number of startups. This article proposes an advanced control system based on the Nonlinear Model Predictive Control (NMPC) technique, which allows to speed up the start-up of steam turbines and increase the energy produced while maintaining rotor stress as a constraint variable. A soft sensor for the online calculation of rotor stress is presented together with the steam turbine control logic. Then, we present how the computational cost of the controller was contained by reducing the order of the formulation of the optimization problem, adjusting the scheduling of the optimizer routine, and tuning the parameters of the controller itself. The performance of the control system has been compared with respect to the PI Controller architecture fed by the soft sensor results and with standard pre-calculated curves. The control architecture was evaluated in a simulation exploiting actual data from a Concentrated Solar Power Plant. The NMPC technique shows an increase in performance, with respect to the custom PI control application, and encouraging results.

No abstract

Network Function Virtualization (NFV) is the key technology that allows modern network operators to provide flexible and efficient services, by leveraging on general-purpose private cloud infrastructures. In this work, we investigate the performance of a number of metric forecasting techniques based on machine learning and artificial intelligence, and provide insights on how they can support the decisions of NFV operation teams. Our analysis focuses on both infrastructure-level and service-level metrics. The former can be fetched directly from the monitoring system of an NFV infrastructure, whereas the latter are typically provided by the monitoring components of the individual virtualized network functions. Our selected forecasting techniques are experimentally evaluated using real-life data, exported from a production environment deployed within some Vodafone NFV data centers. The results show what the compared techniques can achieve in terms of the forecasting accuracy and computational cost required to train them on production data.

Classification of surface defects in the steelworks industry plays a significant role in guaranteeing the quality of the products. From an industrial point of view, a serious concern is represented by the hot-rolled products shape defects and particularly those concerning the strip flatness. Flatness defects are typically divided into four sub-classes depending on which part of the strip is affected and the corresponding shape. In the context of this research, the primary objective is evaluating the improvements of exploiting the self-supervised learning paradigm for defects classification, taking advantage of unlabelled, real, steel strip flatness maps. Different pre-training methods are compared, as well as architectures, taking advantage of well-established neural subnetworks, such as Residual and Inception modules. A systematic approach in evaluating the different performances guarantees a formal verification of the self-supervised pre-training paradigms evaluated hereafter. In particular, pre-training neural networks with the EgoMotion meta-algorithm shows classification improvements over the AutoEncoder technique, which in turn is better performing than a Glorot weight initialization.