Yazar "Yaghoubi, Elnaz" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    State-of-the-art review on energy and load forecasting in microgrids using artificial neural networks, machine learning, and deep learning techniques
    (Elsevier Science Sa, 2023) Wazirali, Raniyah; Yaghoubi, Elnaz; Abujazar, Mohammed Shadi S.; Ahmad, Rami; Vakili, Amir Hossein
    Forecasting renewable energy efficiency significantly impacts system management and operation because more precise forecasts mean reduced risk and improved stability and reliability of the network. There are several methods for forecasting and estimating energy production and demand. This paper discusses the significance of artificial neural network (ANN), machine learning (ML), and Deep Learning (DL) techniques in predicting renewable energy and load demand in various time horizons, including ultra-short-term, short-term, mediumterm, and long-term. The purpose of this study is to comprehensively review the methodologies and applications that utilize the latest developments in ANN, ML, and DL for the purpose of forecasting in microgrids, with the aim of providing a systematic analysis. For this purpose, a comprehensive database from the Web of Science was selected to gather relevant research studies on the topic. This paper provides a comparison and evaluation of all three techniques for forecasting in microgrids using tables. The techniques mentioned here assist electrical engineers in becoming aware of the drawbacks and advantages of ANN, ML, and DL in both load demand and renewable energy forecasting in microgrids, enabling them to choose the best techniques for establishing a sustainable and resilient microgrid ecosystem.
  • Küçük Resim Yok
    Öğe
    A systematic review and meta-analysis of machine learning, deep learning, and ensemble learning approaches in predicting EV charging behavior
    (Pergamon-Elsevier Science Ltd, 2024) Yaghoubi, Elaheh; Yaghoubi, Elnaz; Khamees, Ahmed; Razmi, Darioush; Lu, Tianguang
    Machine learning (ML) and deep learning (DL) have enabled algorithms to autonomously acquire knowledge from data, facilitating predictive and decision-making capabilities without explicit programming. This transformative potential has reshaped industries by utilizing data-driven insights. ML and DL models have found extensive application within the domain of electric vehicle (EV) charging predictions. These techniques effectively forecast EV charging behavior, considering variables such as charging station location, time of day, battery state of charge, EV owner behavioral patterns, and weather conditions. This study aims to comprehensively evaluate ML and DL applications in forecasting EV charging behavior while introducing a systematic categorization, a notable gap in current literature. A comprehensive dataset, selected from both the Web of Science and the Scopus database, sourced from Elsevier Journal, was thoughtfully chosen to cover relevant research studies for the purpose of achieving this goal. Furthermore, our research emphasizes the significance of model evaluation and explores the usefulness of commonly employed ML and DL techniques within forecasting approaches, including Short-Term Load Forecasting (STLF), Medium-Term Load Forecasting (MTLF), and Long-Term Load Forecasting (LTLF) to ensure precise predictions. Within this framework, the selected publications are classified based on methodology, research focus, objectives, publication year, geographic origin, and research outcomes. While both ML and DL techniques exhibit substantial potential in predicting EV charging behavior and mitigating challenges posed by the rising adoption of EVs, our analysis demonstrates that ensemble learning techniques surpass them in terms of predictive performance.
  • Küçük Resim Yok
    Öğe
    Tunable band-pass plasmonic filter and wavelength triple-channel demultiplexer based on square nanodisk resonator in MIM waveguide
    (Elsevier Gmbh, 2022) Faghani, Arman Amiri; Rafiee, Zahra; Amanzadeh, Hamideh; Yaghoubi, Elnaz; Yaghoubi, Elaheh
    This paper proposes a wavelength demultiplexer (WDM) in a metal-insulator-metal (MIM) waveguide based on square cascade resonators, which is numerically simulated using the finite difference time domain (FDTD) approach. WDM's basic construction is a plasmonic filter with two waveguides at the input and output (bass and drop) and a central cavity coupled horizontally to two square nanodisks. The proposed demultiplexer is formed by stacking three examples of these filters and square resonators with different dimensions and with a vertical cavity and a waveguide at the structure's input. The simulation results show that in the designed structure, the Full Width at Half-Maximum (FWHM) in some channels is around 10 nm. The proposed WDM has a cross talk effect of less than 25 dB. In fact, when compared to structures at its level, this structure has a high sensitivity, a low cross talk effect, and a proper Figure of Merit (FoM). If the geometric parameters and insulation's refractive index (RI) are set appropriately, the transmission qualities are able to tune to desired level. The proposed structure has the potential to be utilised in optically integrated circuits, nanosensors, to develop into a 1 x N demultiplexer, and ultracompact plasmonic devices.