Special Issue "The Artificial Intelligence Technologies for Electric Power Systems"

A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "Smart Grids and Microgrids".

Deadline for manuscript submissions: 30 November 2021.

Special Issue Editors

Prof. Pedro NARDELLI
E-Mail Website
Guest Editor
Cyber-physical systems group, LUT University, Lappeenranta, Finland
Interests: cyber-physical systems, industrial IoT, energy management, energy internet, wireless networks, applied artificial intelligence

Special Issue Information

Dear Colleagues,

Artificial Intelligence (AI) is a dynamic topic of research and development in a wide range of fields. Electric power system is no different. This special session is dedicated to the advances of AI techniques applied in this engineering domain. We expect contributions that apply recent advances of AI for tasks related to classification, detection, prediction, diagnosis, analytics, control, planning and management of processes in power systems. Papers dealing with emerging topics such as explainable AI (XAI), deep learning (DL), cyber-security, event-driven/triggered approaches, communication-dependent solutions with low latency enabled by 5G/IoT/edge-computing and software-defined networks are especially welcome. Application domains can range from nano/micro-grids to high-voltage systems, including also topics related to investment plan, demand dispatching, load flexibility, distributed energy resource management and long-term energy storage. In general, all topics that apply cutting-edge AI technologies in electric power systems are equally supported.

We expect to have a session with high-quality publications that Energies readers will enjoy and learn more about the state-of-the-art in the field to move beyond it. We are very happy to answer specific questions of prospective authors.

Prof. Pedro NARDELLI
Prof. Dr. Yongheng Yang
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 papers will be 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 2000 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

  • Artificial intelligence in power system
  • Fault classification, detection, identification, prediction, and diagnosis
  • AI-based demand-side management and flexibility
  • Deep learning
  • Cyber-physical energy systems
  • Communications to support AI in power systems
  • Cyber-security
  • AI-based learning for system optimization

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Sizing and Management of Energy Storage Systems in Large-Scale Power Plants Using Price Control and Artificial Intelligence
Energies 2021, 14(11), 3296; https://doi.org/10.3390/en14113296 - 04 Jun 2021
Viewed by 530
Abstract
Energy storage systems are expected to play a fundamental part in the integration of increasing renewable energy sources into the electric system. They are already used in power plants for different purposes, such as absorbing the effect of intermittent energy sources or providing [...] Read more.
Energy storage systems are expected to play a fundamental part in the integration of increasing renewable energy sources into the electric system. They are already used in power plants for different purposes, such as absorbing the effect of intermittent energy sources or providing ancillary services. For this reason, it is imperative to research managing and sizing methods that make power plants with storage viable and profitable projects. In this paper, a managing method is presented, where particle swarm optimisation is used to reach maximum profits. This method is compared to expert systems, proving that the former achieves better results, while respecting similar rules. The paper further presents a sizing method which uses the previous one to make the power plant as profitable as possible. Finally, both methods are tested through simulations to show their potential. Full article
(This article belongs to the Special Issue The Artificial Intelligence Technologies for Electric Power Systems)
Show Figures

Figure 1

Article
Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization
Energies 2021, 14(6), 1596; https://doi.org/10.3390/en14061596 - 13 Mar 2021
Cited by 11 | Viewed by 939
Abstract
Short-term electrical load forecasting plays an important role in the safety, stability, and sustainability of the power production and scheduling process. An accurate prediction of power load can provide a reliable decision for power system management. To solve the limitation of the existing [...] Read more.
Short-term electrical load forecasting plays an important role in the safety, stability, and sustainability of the power production and scheduling process. An accurate prediction of power load can provide a reliable decision for power system management. To solve the limitation of the existing load forecasting methods in dealing with time-series data, causing the poor stability and non-ideal forecasting accuracy, this paper proposed an attention-based encoder-decoder network with Bayesian optimization to do the accurate short-term power load forecasting. Proposed model is based on an encoder-decoder architecture with a gated recurrent units (GRU) recurrent neural network with high robustness on time-series data modeling. The temporal attention layer focuses on the key features of input data that play a vital role in promoting the prediction accuracy for load forecasting. Finally, the Bayesian optimization method is used to confirm the model’s hyperparameters to achieve optimal predictions. The verification experiments of 24 h load forecasting with real power load data from American Electric Power (AEP) show that the proposed model outperforms other models in terms of prediction accuracy and algorithm stability, providing an effective approach for migrating time-serial power load prediction by deep-learning technology. Full article
(This article belongs to the Special Issue The Artificial Intelligence Technologies for Electric Power Systems)
Show Figures

Figure 1

Article
Noninvasive Detection of Appliance Utilization Patterns in Residential Electricity Demand
Energies 2021, 14(6), 1563; https://doi.org/10.3390/en14061563 - 12 Mar 2021
Viewed by 330
Abstract
Smart meters with automatic meter reading functionalities are becoming popular across the world. As a result, load measurements at various sampling frequencies are now available. Several methods have been proposed to infer device usage characteristics from household load measurements. However, many techniques are [...] Read more.
Smart meters with automatic meter reading functionalities are becoming popular across the world. As a result, load measurements at various sampling frequencies are now available. Several methods have been proposed to infer device usage characteristics from household load measurements. However, many techniques are based on highly intensive computations that incur heavy computational costs; moreover, they often rely on private household information. In this paper, we propose a technique for the detection of appliance utilization patterns using low-computational-cost algorithms that do not require any information about households. Appliance utilization patterns are identified only from the system status behavior, represented by large system status datasets, by using dimensionality reduction and clustering algorithms. Principal component analysis, k-means, and the elbow method are used to define the clusters, and the minimum spanning tree is used to visualize the results that show the appearance of utilization patterns. Self organizing maps are used to create a system status classifier. We applied our techniques to two public datasets from two different countries, the United Kingdom (UK-DALE) and the US (REDD), with different usage patterns. The proposed clustering techniques enable effective demand-side management, while the system status classifier can detect appliance malfunctions only through system status analyses. Full article
(This article belongs to the Special Issue The Artificial Intelligence Technologies for Electric Power Systems)
Show Figures

Figure 1

Article
Dual Two-Level Voltage Source Inverter Virtual Inertia Emulation: A Comparative Study
Energies 2021, 14(4), 1160; https://doi.org/10.3390/en14041160 - 22 Feb 2021
Viewed by 471
Abstract
In this paper, the virtual synchronous generator (VSG) concept is utilized in the controller of the grid-connected dual two-level voltage source inverter (DTL VSI). First, the topology of the VSG and the DTL VSI are presented. Then, the state-space equations of the DTL [...] Read more.
In this paper, the virtual synchronous generator (VSG) concept is utilized in the controller of the grid-connected dual two-level voltage source inverter (DTL VSI). First, the topology of the VSG and the DTL VSI are presented. Then, the state-space equations of the DTL VSI and the grid-connected two-level voltage source inverter (TL VSI), regarding the presence of the phase-locked loop (PLL) and the VSG, are given. Next, the small-signal modeling of the DTL VSI and the TL VSI is realized. Eventually, the stability enhancement in the DTL VSI compared with the TL VSI is demonstrated. In the TL VSI, large values of virtual inertia could result in oscillations in the power system. However, the ability of the DTL VSI in damping oscillations is deduced. Furthermore, in the presence of nonlinear loads, the potentiality of the DTL VSI in reducing grid current Total Harmonic Distortion (THD) is evaluated. Finally, by using a proper reference current command signal, the abilities of the DTL VSI and the TL VSI in supplying nonlinear loads and providing virtual inertia are assessed simultaneously. The simulation results prove the advantages of the DTL VSI compared with the TL VSI in virtual inertia emulation and oscillation damping, which are realized by small-signal analysis. Full article
(This article belongs to the Special Issue The Artificial Intelligence Technologies for Electric Power Systems)
Show Figures

Figure 1

Article
Production Line Optimization to Minimize Energy Cost and Participate in Demand Response Events
Energies 2021, 14(2), 462; https://doi.org/10.3390/en14020462 - 16 Jan 2021
Viewed by 717
Abstract
The scheduling of tasks in a production line is a complex problem that needs to take into account several constraints, such as product deadlines and machine limitations. With innovative focus, the main constraint that will be addressed in this paper, and that usually [...] Read more.
The scheduling of tasks in a production line is a complex problem that needs to take into account several constraints, such as product deadlines and machine limitations. With innovative focus, the main constraint that will be addressed in this paper, and that usually is not considered, is the energy consumption cost in the production line. For that, an approach based on genetic algorithms is proposed and implemented. The use of local energy generation, especially from renewable sources, and the possibility of having multiple energy providers allow the user to manage its consumption according to energy prices and energy availability. The proposed solution takes into account the energy availability of renewable sources and energy prices to optimize the scheduling of a production line using a genetic algorithm with multiple constraints. The proposed algorithm also enables a production line to participate in demand response events by shifting its production, by using the flexibility of production lines. A case study using real production data that represents a textile industry is presented, where the tasks for six days are scheduled. During the week, a demand response event is launched, and the proposed algorithm shifts the consumption by changing task orders and machine usage. Full article
(This article belongs to the Special Issue The Artificial Intelligence Technologies for Electric Power Systems)
Show Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Production line optimization to minimize energy cost and participate in demand response events
Authors: Bruno Mota, Luis Gomes, Pedro Faria, Carlos Ramos, and Zita Vale
Affiliation: Knowledge Engineering and Decision-Support Research Center, Portugal
Abstract: The scheduling of tasks in a production line is a complex problem that needs to take into account several constraints, such as product deadlines, and machine limits. The main constraint that will be addressed in this paper, and that usually is not considered, is the energy consumption cost of the production line. For that, a genetic-algorithm based method is proposed. Currently, the use of local energy generation, especially from renewable sources, and the possibility of having multiple energy providers will allow the user to manage its consumption according to energy prices and energy availability. The proposed solution will take into account the energy availability of renewable sources and energy prices to optimize the scheduling of a production line using a genetic algorithm with multiple constraints. The proposed algorithm also enables a production line to participate in demand response programs by shifting its production, enabling the use of flexibility in production lines. This paper presents a case study using real production data that represents a textile industry where the tasks for six days are scheduled. During the week, a demand response program will be launched and the proposed algorithm will shift the consumption by changing tasks orders and machine usage.

Back to TopTop