[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.2
3.0
Journals
Energies
Special Issues
Computational Intelligence in Electrical Systems: 2nd Edition
energies-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Energies Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Computational Intelligence in Electrical Systems: 2nd Edition

A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "F: Electrical Engineering".

Deadline for manuscript submissions: 15 May 2025 | Viewed by 499

Special Issue Editors

Prof. Dr. Massimo Panella

E-Mail Website
Guest Editor
Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Via Eudossiana 18, 00184 Rome, Italy
Interests: deep learning; computational intelligence; smart sensor networks; quantum computing
Special Issues, Collections and Topics in MDPI journals
Dr. Antonello Rosato

E-Mail
Guest Editor
Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Via Eudossiana 18, 00184 Rome, Italy
Interests: machine learning techniques for time series analysis and forecasting; distributed learning algorithms; neural and fuzzy neural models for ICT and industrial applications
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Rodolfo Araneo

E-Mail Website
Guest Editor
Department of Astronautical, Electrical and Energetic Engineering University of Rome La Sapienza Via Eudossiana 18, 00184 Rome, Italy
Interests: electromagnetic compatibility; energy harvesting; graphene electrodynamics; numerical and analytical techniques for modeling high-speed printed circuit boards; shielding; transmission lines; periodic structures; devices based on graphene
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Electrical systems are central in the energy transition from fossil fuels to renewables. Toward this end, it is essential that final prosumers can collectively cooperate in the management of distributed energy resources (DERs) to share energy and assets. Distributed resources in an energy community can be geographically near, sharing a smart microgrid conceived as a set of renewable energy sources (RESs), loads, energy storage systems (ESSs), and electric vehicles (EVs).

In this scenario, data-driven modeling techniques play a crucial role based on the machine learning paradigm and, more generally, computational intelligence in synergy with ICT technologies that help share information across complex infrastructures. Many control, decision, and optimization problems for electrical systems should be handled with real-time constraints while involving a large amount of data in complex operation frameworks. Consequently, such tasks should be solved using distributed learning techniques, as they cannot be handled by a centralized authority (i.e., for privacy concerns, networking reliability, etc.), nor can they be carried out efficiently by human operators.

This Special Issue is intended to bring forth advances in the use of computational intelligence tools (shallow and deep neural networks, fuzzy systems, evolutionary computation, etc.) in connection with statistical machine learning and signal processing techniques to solve real-world problems related to electrical systems. Special attention should be paid to the distributed contexts of smart grid, RES, ESS, and EV infrastructures, as well as to the energy/power aspects in ICT technologies and the related applications as, for instance, hungry data centers, green computing and green networking, EMC/EMI, energy harvesting, low-power micro/nano/optoelectronic systems, and so forth. Strategic tasks are pattern analysis, data regression and classification, optimization and control, decision-making, and time series forecasting.

Prof. Dr. Massimo Panella
Dr. Antonello Rosato
Prof. Dr. Rodolfo Araneo
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Energies is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • smart grids, microgrids, and virtual power plants
  • distributed energy resources
  • renewable energy sources
  • energy storage systems
  • electric vehicles
  • green computing and green networking
  • energy harvesting
  • low-power ICT systems
  • neural networks
  • fuzzy systems
  • evolutionary computation
  • deep learning
  • classification and clustering
  • data regression optimization and control
  • time series
  • forecasting

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Related Special Issue

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

22 pages, 5950 KiB  
Article
Clustering Analysis for Active and Reactive Energy Consumption Data Based on AMI Measurements
by Oscar A. Bustos-Brinez and Javier Rosero Garcia
Energies 2025, 18(1), 221; https://doi.org/10.3390/en18010221 - 6 Jan 2025
Viewed by 220
Abstract
Electrical data analysis based on smart grids has become a fundamental tool used by electrical grid stakeholders to understand the energy consumption patterns of users, although many proposals in this area do not consider reactive energy as another source of useful information regarding [...] Read more.
Electrical data analysis based on smart grids has become a fundamental tool used by electrical grid stakeholders to understand the energy consumption patterns of users, although many proposals in this area do not consider reactive energy as another source of useful information regarding distribution costs and threats to the grid. In this regard, the analysis of reactive energy patterns can become an extremely useful addition to existing electrical data analysis frameworks. This work shows the application of a series of clustering techniques over measurements of both active and reactive energy consumption measured for end users from the Colombian electrical network, including an analysis of the efficiency of the network measured by calculating the ratio of active energy to total consumption (power factor) per user. This allows a detailed characterization of users to be compiled, based on the identification of different active and reactive energy consumption behaviors, which could help grid operators to improve overall grid management and to increase the efficiency of their reactive energy compensation strategies. Full article
(This article belongs to the Special Issue Computational Intelligence in Electrical Systems: 2nd Edition)
►▼ Show Figures

Figure 1

Figure 1
<p>Visual summary of the methodology, presented as a series of consecutive steps. From left to right, it starts with the preprocessing of the original data to discard users with missing values and isolate registers from different months. In each month, information is separated into five measurements (two for active energy, two for reactive energy, and power factor) and each one is passed to the clustering methods, on which a parameter search is performed. Finally, some of the results of the best clusters are used to perform the detection of anomalous consumption patterns.</p> Full article ">Figure 2
<p>Statistical analysis over consumption profiles (hour by hour), showing interquartile ranges as colored box plots, and average (mean) values as a green line connecting through all hours. Section (<b>a</b>) shows the results of this analysis for active profiles, and section (<b>b</b>) the results for reactive profiles.</p> Full article ">Figure 3
<p>Statistical analysis over consumption data grouped by day of the week, showing interquartile ranges as colored box plots, and average (mean) values as a green line connecting through all week days. Section (<b>a</b>) shows the results of this analysis for active profiles, and section (<b>b</b>) the results for reactive profiles.</p> Full article ">Figure 4
<p>Cluster averages (centroids) obtained by applying the best clustering method on active energy user profiles. Section (<b>a</b>) shows the results for active profiles considering magnitude, and section (<b>b</b>) shows the results for normalized active profiles.</p> Full article ">Figure 5
<p>Cluster averages (centroids) obtained by applying the best clustering method on reactive energy user profiles. Section (<b>a</b>) shows the results for reactive profiles considering magnitude, and section (<b>b</b>) shows the results for normalized reactive profiles.</p> Full article ">Figure 6
<p>Results of the segmentation of users based on power factor values. Since the results are pretty similar for the four months, section (<b>a</b>) shows the centroids of the three clusters obtained in a particular month to showcase the levels around which each cluster is centered. Section (<b>b</b>) is a bar plot that presents the relative weight of the three clusters for each month, showing that the total of users is roughly divided 51%/45%/4% among the three clusters.</p> Full article ">Figure 7
<p>Statistical exploration of the consumption magnitude of users, when grouped by the three power factor clusters. For each month, the distribution of magnitudes of active and reactive consumption is shown as a violin plot discriminated by clusters. Each color represents the same cluster in all plots, and cluster colors and numbers (0, 1, 2) also coincide with the ones shown in <a href="#energies-18-00221-f006" class="html-fig">Figure 6</a>.</p> Full article ">Figure 8
<p>Examples of profile curves associated with users in each one of the six groups defined in <a href="#energies-18-00221-t003" class="html-table">Table 3</a>. From top to bottom, high, medium and low consumption magnitudes; from left to right, normal and anomalous behaviors.</p> Full article ">Figure 9
<p>Examples of profile curves associated groups of users defined in <a href="#energies-18-00221-t004" class="html-table">Table 4</a>. Left column, users with both normal active and reactive profiles. Middle column, users with one normal profile and one anomalous profile. Right column, users with both anomalous active and reactive profiles.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop