CNN-LSTM for Secure Distributed Demand Response in Smart Grid DOI
Aschalew Tirulo, Siddhartha Chauhan

Published: Nov. 22, 2023

Integrating cyber and physical elements in smart grids amplifies susceptibility to false data injection attacks (FDIAs), jeopardizing home automation energy infrastructure. Traditional security strategies often underperform FDIA detection due varied origins. We propose an advanced anomaly framework using CNN-LSTM, tailored detect FDIAs the grid's demand response. Our model employs supervised learning for improved precision when enriched with label information. Empirical tests genuine from Austin, Texas, demonstrate our model's superiority over existing methods, metrics like accuracy, precision, recall, F1 score, positive rate consistently affirming its robustness real-world applicability.

Language: Английский

Contributions of artificial intelligence and digitization in achieving clean and affordable energy DOI Creative Commons
Omojola Awogbemi, Daramy Vandi Von Kallon, K. Sunil Kumar

et al.

Intelligent Systems with Applications, Journal Year: 2024, Volume and Issue: 22, P. 200389 - 200389

Published: May 19, 2024

Concerned by the continuous decline in quality of life, poverty, environmental degradation, and escalated war conflicts, United Nations 2015 instituted 17 Sustainable Development Goals (SDGs) 169 targets. Access to clean, modern, affordable energy, also known as SDG 7, is one goals. Universal access electricity metrics for measuring a good life it fundamentally affects education, healthcare, food security, job creation, other socioeconomic indices. To achieve this goal targets, there has been increased traction research, development, actionable plans, policies, activities governments, scientific community, environmentalists, development experts, stakeholders achieving goal. This review presents various avenues which AI digitization can provide impetus 7. The global trends attaining clean electricity, cooking fuel, renewable energy efficiency, international public financial flows between 2005 2021 are reviewed while contribution towards meeting 7 highlighted. study concludes that deployment into sector will catalyze attainment 2030, provided ethical issues, regulatory concerns, manpower shortage, shortcomings effectively handled. recommends adequate infrastructural upgrades, modernization data collection, storage, analysis capabilities, improved awareness professional collaborative innovation, promotion legal issues ways advancing universal 2030. Going forward, more collaborations academic research institutions producers help produce experts professionals propel innovative digital technologies sector.

Language: Английский

Citations

14
Global Renewable Energy Transition: A Multidisciplinary Analysis of Emerging Computing Technologies, Socio-Economic Impacts, and Policy Imperatives DOI Creative Commons

Herman Zahid,

Adil Zulfiqar, Muhammad Gufran Khan

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 105258 - 105258

Published: May 1, 2025

Language: Английский

Citations

0
NeuroQuMan: quantum neural network-based consumer reaction time demand response predictive management DOI
Ashkan Safari, Mohammad Ali Badamchizadeh

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: 36(30), P. 19121 - 19138

Published: Aug. 2, 2024

Language: Английский

Citations

2
S3: Sneaky Spectral Strike Trojan Attacks on Deep Learning-based Time Series Smart Grid Models DOI Creative Commons
Sultan Uddin Khan, Mohammed Mynuddin, Mahmoud Nabil

et al.

Published: Jan. 2, 2024

Deep learning (DL) has gained prominence as an effective approach for enhancing the efficiency of various applications including smart grids (SG). Although these models excel significantly in classification tasks power quality disturbances, their vulnerability to trojan attacks introduces potential complications. In this paper, we introduce two novel algorithms executing on DL handling time series data SG, tailored both white-box and black-box. For white-box, our algorithm titled 'Sneaky Spectral Strike (S 3)' utilizes frequency domain trigger optimization perform attacks, which demonstrates a remarkable average fooling rate 99.9% across models. The also balances signal-to-noise ratio, model accuracy clean data, be highly imperceptible human observers control center (PCC). black-box, propose algorithm, 'Lite Datanet Sneaky Strike', that integrates simple with small sample dataset create triggers are effective, stealthy, transferable deployed PCC. This achieves 99.86% different advanced models, highlighting effectiveness resource-efficient strategies DL-based SG. Both underscore vulnerabilities used SG , mark significant advancement adversarial machine learning.

Language: Английский

Citations

1
THE ROLE OF INFORMATION AND COMMUNICATION TECHNOLOGY IN CLIMATE CHANGE MITIGATION AND ADAPTATION. DOI Open Access

Okeoma Onunka,

Ochuko Felix Orikpete,

Chibuike Daraojimba

et al.

Ecofeminism and Climate Change, Journal Year: 2023, Volume and Issue: 4(2), P. 102 - 111

Published: June 20, 2023

In an era marked by the escalating implications of climate change, importance Information and Communication Technology (ICT) cannot be overemphasised. This paper elucidates multifaceted roles ICT in both mitigation adaptation to change. On front, offers tools for monitoring modelling greenhouse gas emissions, optimising energy consumption, facilitating transition renewable sources. terms adaptation, enhances prediction management climate-induced risks, supports real-time communication during extreme weather events, aids planning implementation resilient infrastructure. Moreover, bolsters science diverse audiences, fostering education advocacy. However, while potential is significant, challenges such as e-waste, consumption data centres, digital divides necessitate holistic strategies maximise ICT’s positive impact. underscores need informed policy-making, integration with traditional ecological knowledge, interdisciplinary collaboration leverage effectively global response.

Language: Английский

Citations

2
Load Frequency Control in Two Area Power Systems in A Smart Grid Environment DOI

Faradji Mohamed,

Toufik Madani Layadi,

İlhami Çolak

et al.

Published: May 27, 2024

Language: Английский

Citations

0
Development of a Low-Cost Automated Demand Response Controller for Home Energy Management DOI Creative Commons
Yu‐Chi Wu,

Chao-Shu Chang,

Wenhui Li

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(23), P. 11434 - 11434

Published: Dec. 9, 2024

This research focuses on developing a low-cost automated demand response controller (DRC) with OpenADR 2.0a capability to enable existing infrared-controlled (IR-controlled) air conditioners (ACs) in homes and buildings participate programs (ADRPs). The DRC consists of four modules: smart socket module, an infrared temperature sensor, voltage/current module. It can receive, analyze, respond (DR) events perform necessary energy control strategies via IR. Power line communication (PLC) is used for without additional wiring. system tested under two conditions: participating ADRPs not ADRPs. An 8.8% load reduction observed different settings when ADRPs, reductions 21% 46% are achieved using various cooling/fanning duty cycles proposed be integrated any DR algorithm meet management requirements the program, contributing significant reductions.

Language: Английский

Citations

0
Using Synchronization as an Indicator of Controllability in a Fleet of Water Heaters DOI

Eve Tsybina,

Viswadeep Lebakula, Justin Hill

et al.

2021 North American Power Symposium (NAPS), Journal Year: 2023, Volume and Issue: unknown, P. 1 - 6

Published: Oct. 15, 2023

Peak reduction is an important concern that can help reduce the growing stress on distribution grid and allow to defer investments in new capacity. However, for customer privacy comfort may impact performance of load control residential devices. Water heaters represent a convenient way reducing peak due their ability store thermal energy future use. In this paper, we developed methodology utilities gain more insight with respect efforts shaving no necessary information about water except device status (on/off). To end, use fleet controlled neighborhood Atlanta, GA. Our findings show convergence serve as proxy shifting during hours evening peak.

Language: Английский

Citations

1
Demand-Side Management as a Network Planning Tool: Review of Drivers, Benefits and Opportunities for South Africa DOI Creative Commons
Mukovhe Ratshitanga, Haltor Mataifa, Senthil Krishnamurthy

et al.

Energies, Journal Year: 2023, Volume and Issue: 17(1), P. 116 - 116

Published: Dec. 25, 2023

The reliability and security of an electric power supply have become pivotal to the proper functioning modern society. Traditionally, system has been designed with objective being able adequately meet present future demand, efforts maintain focused primarily on side. Over decades, however, value demand-side management—efforts enhancing efficient effective use electricity in support customer needs—has widely acknowledged as play a greater role ensuring that key objectives operation are satisfied. This article presents study management opportunities for incorporating it into network planning means addressing capacity constraints South African grid. main drivers, benefits potential barriers implementation examined, along enabling technologies. finding is integration requires shift from traditional approach one more suited fully exploiting flexibility resources available demand side network.

Language: Английский

Citations

1
Explainable Neural Dynamics Models for Motor Temperature Prediction DOI Creative Commons
Xinyuan Liao, Shaowei Chen,

Yunxiang Long

et al.

Published: Nov. 13, 2023

<p> The permanent magnet synchronous motor finds extensive use in industrial applications, and the development of effective thermal management solutions is crucial to enhance its power density. Accurate temperature prediction serves as fundamental basis for designing strategies. Model-based methods exhibit superior real-time performance, but intricate modeling process requires substantial expert knowledge guidance lacks versatility. Conversely, data-driven methods, while offering flexibility, often lack physical implications terms system dynamics. This paper proposed a structured linear neural dynamics model prediction. data-driven, with prior integrated into structure, which preserves flexibility guaranteeing stability through Perron-Frobenius theorem. Additionally, this achieves decoupling control input from state transitions embedded deployment model. method validated real dataset. lightweight feature demonstrated by implementation an STM32 Microcontroller 1.808 KB 27 mW. accompanied open source data code at GitHub https://github.com/ms140429/Explainable-Neural-Dynamics-Model</p>

Language: Английский

Citations

0