In this paper, we approach the problem of forecasting a time series (TS) an electrical load measured on Azienda Comunale Energia e Ambiente (ACEA) power grid, company managing electricity distribution in Rome, Italy, with echo state network (ESN) considering two different leading times 10 min and 1 day. We use standard for predicting next min, while, forecast horizon one day, represent data high-dimensional multi-variate TS, where number variables is equivalent to quantity measurements...

The year 2020 opened with a dramatic epidemic caused by new species of coronavirus that soon has been declared pandemic the WHO due to high number deaths and critical mass worldwide hospitalized patients, order millions. COVID-19 forced governments hundreds countries apply several heavy restrictions in citizens' socio-economic life. Italy was one most affected long-term restrictions, impacting tissue. During this lockdown period, people got informed mostly on Online Social Media, where...

The introduction of Transformer architectures – with the self-attention mechanism in automatic Natural Language Generation (NLG) is a breakthrough solving general task-oriented problems, such as simple production long text excerpts that resemble ones written by humans. While performance GPT-X there for all to see, many efforts are underway penetrate secrets these black-boxes terms intelligent information processing whose output statistical distributions natural language. In this work,...

In this paper we present an interesting application of Computational Intelligence techniques for the power demand side and flow management optimization in a microgrid. particular, used Fuzzy Logic Controller (FLC) Time-of use Cost Management program FLC can either sell buy energy from outside microgrid making aggregate storage capacity realized with lithium ion batteries. According to hybrid Fuzzy-GA paradigm, that operates decision on flows is optimized by Genetic Algorithm. The...

This paper presents a novel power flow optimization strategy for Grid Connected microgrid (MG) equipped with Battery Energy Storage System (BESS), namely Li-Ion battery pack. A BESS can be employed to perform several functionalities, related different user requirements, such as stability, peak shaving, optimal energy trading, etc. In the proposed system MG is composed by an aggregation of distributed generators and loads adopted manage over-production/over-demand in real time, order maximize...

One notable paradigm shift in Natural Language Processing has been the introduction of Transformers, revolutionizing language modeling as Convolutional Neural Networks did for Computer Vision. The power along with many other innovative features, also lies integration word embedding techniques, traditionally used to represent words a text and build classification systems directly. This study delves into comparison representation techniques classifying users who generate medical topic posts on...

Abstract The problem of the information representation and interpretation coming from senses by brain has plagued scientists for decades. same problems, a different perspective, hold in automated Pattern Recognition systems. Specifically, solving various NLP tasks, an ever better richer semantic text as set features is needed plethora embedding techniques algebraic spaces are continuously provided researchers. These well suited to be conceived conceptual light Gärdenfors’s Conceptual Space...

This paper presents a novel power flow optimization strategy in Micro Grids (MGs) connected to the main grid. When MG includes stochastic energy sources, such as photovoltaic and micro eolic-generators, it is very useful rely on Energy Storage Systems (ESSs) buffer energy. In fact, an ESS can be employed perform several functionalities, related different user requirements, stability, peak shaving, optimal trading, etc. The Management System based Fuzzy Logic Controller (FLC) optimized by...

Modeling and recognizing events in complex systems through machine learning techniques is a challenging task. Especially if the model constrained to be explainable interpretable, while ensuring high levels of accuracy. In this paper, we adopt bilinear logistic regression which parameters are trained data-driven fashion on real-world dataset power grid failure data. The white-box - grounded specific neural architecture has been proven effective classifying faulty states with performance...

The study of languages' structure and their organization in a set well-defined relation schemes is delicate matter. In the last decades, convergence traditional conflicting views by linguists supported an interdisciplinary approach that involves not only genetics or bio-archelogy but nowadays even science complexity. light this new useful approach, proposes in-depth analysis complexity underlying morphological organization, terms multifractality long-range correlations, several modern...

Dissimilarity spaces, along with feature reduction/ selection techniques, are among the mainstream approaches when dealing pattern recognition problems in structured (and possibly non-metric) domains. In this work, we aim at investigating dissimilarity space representations a biology-related application, namely protein function classification, as proteins seminal example of data given their primary and tertiary structures. Specifically, propose two different analyses relying on both complete...

The worldwide power grid can be thought as a System of Systems deeply embedded in time-varying, non-deterministic and stochastic environment. availability ubiquitous pervasive technology about heterogeneous data gathering information processing the Smart Grids allows new methodologies to face challenging task fault detection modeling. In this study, recognition system for Medium Voltage feeders operational Rome, Italy, is presented. performed synthesizing data-driven model phenomenons based...

Calibrating a classification system consists in transforming the output scores, which somehow state confidence of classifier regarding predicted output, into proper probability estimates. Having well-calibrated has non-negligible impact on many real-world applications, for example decision making systems synthesis anomaly detection/fault prediction. In such industrial scenarios, risk assessment is certainly related to costs must be covered. this paper we review three state-of-the-art...

Efforts in the fight against Climate Change are increasingly oriented towards new energy efficiency strategies Smart Grids (SGs). In 2018, with proper legislation, European Union (EU) defined Renewable Energy Community (REC) as a local electrical grid whose participants share their self-produced renewable energy, aiming at reducing bill costs by taking advantage of incentives. That action aspires to accelerate spread exploitation, could not be within everyone's reach. Since REC is...

Natural language processing and text mining applications have gained a growing attention diffusion in the computer science machine learning communities. In this work, new embedding scheme is proposed for solving classification problems. The relies on statistical assessment of relevant words within corpus using compound index originally ecology: allows to spot parts overall (e.g., words) top which performed following Granular Computing approach. employment statistically meaningful not only...

The analysis and recognition of fault status in the Smart Grid field is a challenging problem. Computational Intelligence techniques have already been shown to be successful framework face complex problems related Grid. availability huge amounts data coming from smart sensors allows system take fine grained picture power grid status. This can processed order offer an instrument aiding humans operators better understand decisions on operations. paper addresses problem recognitions real-world...

Due to the intrinsic complexity of real-world power distribution lines, which are highly non-linear and time-varying systems, modeling predicting a general fault instance is very challenging task. Power outages can be experienced as consequence multitude causes, such damage some physical components or grid overloads. Smart grids equipped with sensors that enable continuous monitoring status, hence allowing realization control systems related different optimization tasks, effectively faced by...

Abstract Machine Learning is currently a well-suited approach widely adopted for solving data-driven problems in predictive maintenance. Data-driven approaches can be used as the main building block risk-based assessment and analysis tools Transmission Distribution System Operators modern Smart Grids. For this purpose, suitable Decision Support should able of providing not only early warnings, such detection faults real time, but even an accurate probability estimate outages failures. In...

Due to the increasing amount of sensors and data streams that can be collected in order monitor electric distribution networks, developing predictive diagnostic systems over Smart Grids demands powerful scalable algorithms search for regularities Big Data. In this regards, Evolutive Agent Based Clustering (E-ABC) is a promising framing reference, as it conceived orchestrate swarm intelligent agents acting individuals an evolving population, each performing random walk on different subset...