Data Augmentation Technique Based on Improved Time-Series Generative Adversarial Networks for Power Load Forecasting in Recirculating Aquaculture Systems DOI Open Access
Jun Li,

Xingzhao Zhang,

Qingsong Hu

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(23), P. 10721 - 10721

Published: Dec. 6, 2024

Factory aquaculture faces a difficult situation due to its high running costs, with one of the main contributing factors being energy consumption workshops. Accurately predicting power load recirculating systems (RAS) is critical optimizing use, reducing consumption, and promoting sustainable development factory aquaculture. Adequate data can improve accuracy prediction model. However, there are often missing abnormal in actual detection. To solve this problem, study uses time-series convolutional network–temporal sequence generation adversarial network (TCN-TimeGAN) synthesize multivariate RAS train long short-term memory (LSTM) on original generated predict future electricity loads. The experimental results show that based improved TCN-TimeGAN provide more comprehensive coverage distribution, lower discriminative score (0.2419) predictive (0.0668) than conventional TimeGAN. Using for prediction, R2 reached 0.86, which represents 19% improvement over ARIMA Meanwhile, compared LSTM GRU without augmentation, mean absolute error (MAE) was reduced by 1.24 1.58, respectively. model has good performance generalization ability, benefits saving, production planning, term sustainability

Language: Английский

The Role of Utilizing Artificial Intelligence and Renewable Energy in Reaching Sustainable Development Goals DOI
Fatma M. Talaat, A.E. Kabeel,

Warda M. Shaban

et al.

Renewable Energy, Journal Year: 2024, Volume and Issue: 235, P. 121311 - 121311

Published: Sept. 7, 2024

Language: Английский

Citations

11
Fuzzy logic-supported building design for low-energy consumption in urban environments DOI Creative Commons

M. Arun,

Cristina Efremov, Van Nhanh Nguyen

et al.

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 105384 - 105384

Published: Oct. 1, 2024

Language: Английский

Citations

8
Deep Learning for Wind and Solar Energy Forecasting in Hydrogen Production DOI Creative Commons
Artūrs Ņikuļins, Kaspars Sudars, Edgars Edelmers

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(5), P. 1053 - 1053

Published: Feb. 23, 2024

This research delineates a pivotal advancement in the domain of sustainable energy systems, with focused emphasis on integration renewable sources—predominantly wind and solar power—into hydrogen production paradigm. At core this scientific endeavor is formulation implementation deep-learning-based framework for short-term localized weather forecasting, specifically designed to enhance efficiency derived from sources. The study presents comprehensive evaluation efficacy fully connected neural networks (FCNs) convolutional (CNNs) within realm deep learning, aimed at refining accuracy forecasts. These methodologies have demonstrated remarkable proficiency navigating inherent complexities variabilities associated thereby significantly improving reliability precision predictions pertaining output. cornerstone investigation deployment an artificial intelligence (AI)-driven forecasting system, which meticulously analyzes data procured 25 distinct monitoring stations across Latvia. system tailored deliver (1 h ahead) forecasts, employing sensor fusion approach accurately predicting power outputs. A major finding achievement mean squared error (MSE) 1.36 model, underscoring potential optimizing utilization production. Furthermore, paper elucidates construction revealing that enhances model’s predictive capabilities by leveraging multiple sources generate more accurate robust forecast. entire codebase developed during has been made available open access GIT server.

Language: Английский

Citations

5
Renewable Electricity Management Cloud System for Smart Communities Using Advanced Machine Learning DOI Creative Commons

Yukta Mehta,

Vincent Lo,

Vihang Mehta

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(6), P. 1418 - 1418

Published: March 13, 2025

Based on the renewable energy assessment in 2023, it was found that only 21% of total electricity is generated using sources. As global demand for rises AI world, need management will increase and must be optimized. research, many companies are working green management, but few predicting shortages. To identify rising demand, predict shortage, to bring attention consumption, this study focuses optimization solar generation, tracking its forecasting shortages well advance. This system demonstrates a novel approach advanced machine learning, deep reinforcement learning maximize utilization. paper proposes develops community-based model manages analyzes multiple buildings’ usage, allowing perform both distributed aggregated decision-making, achieving an accuracy 98.2% stacking results models with learning. Concerning real-world problem, provides sustainable solution by combining data-driven contributing current market need.

Language: Английский

Citations

0
Smart Forecasting With AI DOI
Muhammad Usman Tariq

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 165 - 184

Published: Feb. 7, 2025

The use of smart forecasting in artificial intelligence (AI) to transform energy storage and consumption is examined this chapter. Artificial revolutionizing the systems industry particularly areas grids management renewable by analysing large volumes data finding patterns. In order predict generation maintain grid stability maximize chapter explores crucial roles that AI machine learning play. Additionally, it emphasizes how big data, can be combined increase accuracy which has important ramifications for sources like solar wind. effective commodity market operations demonstrated real-world case studies. Chapter also addresses ethical social issues deployment focusing on cooperation with human expertise.

Language: Английский

Citations

0
Evolving Electricity Demand Modelling in Microgrids Using a Kolmogorov-Arnold Network DOI

Stefano Sanfilippo,

José Juan Hernández-Gálvez,

José Juan Hernández-Cabrera

et al.

Informatica, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 22

Published: Jan. 1, 2025

Electricity demand estimation is vital for the optimal design and operation of microgrids, especially in isolated, unelectrified, or partially electrified areas where patterns evolve with electricity adoption. This study proposes a causal model that explicitly considers electrification process along key factors such as hour, month, weekday/weekend distinction, temperature, humidity, effectively capturing both temporal environmental patterns. To capture process, “Degree Adoption” factor has been included, making it distinctive feature this approach. Through variable, accounts evolving growth usage, an essential consideration accurately estimating newly electrifying consumers gain access to integrate new electrical appliances. Another contribution successful application Kolmogorov–Arnold Network (KAN), architecture designed complex nonlinear relationships more than conventional neural networks rely on standard activation functions, ReLU sigmoid. validate effectiveness proposed modelling approaches, comprehensive experiments were conducted using dataset covering 578 days consumption from El Espino, Bolivia. enabled robust comparisons among KAN network architectures, Deep Feedforward Neural (DFNN) Multi-Layer Perceptron (MLP), while also assessing impact incorporating Degree Adoption factor. The empirical results clearly demonstrate KAN, combined Adoption, achieved superior performance, obtaining error 0.042, compared DFNN (0.049) MLP (0.09). Additionally, integrating significantly enhanced by reducing approximately 10%. These findings adoption dynamics confirm KAN’s relevance estimation, highlighting its potential support microgrid operation.

Language: Английский

Citations

0
Enhanced Reactive Power Compensation for Flicker Mitigation in Wind Farm-Integrated Distribution Networks Using Advanced D-STATCOM Control DOI Creative Commons
Kevin Joel Vela Palaquibay, Manuel Jaramillo, Diego Carrión

et al.

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 241 - 251

Published: Jan. 1, 2025

Language: Английский

Citations

0
Forecasting Electricity Consumption Using Function Fitting Artificial Neural Networks and Regression Methods DOI Creative Commons
André Gifalli, Haroldo Luiz Moretti do Amaral, Alfredo Bonini Neto

et al.

Applied System Innovation, Journal Year: 2024, Volume and Issue: 7(5), P. 100 - 100

Published: Oct. 18, 2024

With the growth of smart grids, consumers now have access to new technologies that enable improvements in quality service provided and allow levels energy efficiency. Much this increase efficiency is directly related changes consumption habits due quantity information made available by technologies. At point, short-term forecasting can be considered an effective tool search for better patterns This paper presents prediction tests combining result obtained from artificial neural network regression methods. The used was Multilayer Perceptron (MLP), its results were compared with polynomial techniques (first, second, third degree), demonstrating superiority network. has proven a highly future data, ability capture complex input data produce accurate estimates. Additionally, flexibility networks handling large volumes their continuous adjustment capability further enhance suitability as robust predictions. corroborate capacity methodology presented forecasting.

Language: Английский

Citations

3
Hydropower Station Status Prediction Using RNN and LSTM Algorithms for Fault Detection DOI Creative Commons

Omar Farhan Al-Hardanee,

Hüseyi̇n Demi̇rel

Energies, Journal Year: 2024, Volume and Issue: 17(22), P. 5599 - 5599

Published: Nov. 9, 2024

In 2019, more than 16% of the globe’s total production electricity was provided by hydroelectric power plants. The core a typical plant is turbine. Turbines are subjected to high levels pressure, vibration, temperatures, and air gaps as water passes through them. Turbine blades weighing several tons break due this surge, tragic accident because massive damage they cause. This research aims develop predictive models accurately predict status plants based on real stored data for all factors affecting these importance having model future lies in avoiding turbine blade breakage catastrophic accidents resulting damages, increasing life plants, sudden shutdowns, ensuring stability generation electrical energy. study, artificial neural network algorithms (RNN LSTM) used condition hydropower station, identify fault before it occurs, avoid it. After testing, LSTM algorithm achieved greatest results with regard highest accuracy least error. According findings, attained an 99.55%, mean square error (MSE) 0.0072, absolute (MAE) 0.0053.

Language: Английский

Citations

1
Tackling security and privacy challenges in the realm of big data analytics DOI Creative Commons

Janet Ngesa

World Journal of Advanced Research and Reviews, Journal Year: 2023, Volume and Issue: 21(2), P. 552 - 576

Published: Feb. 28, 2023

As organizations increasingly harness the power of big data analytics to derive insights and drive decision-making, paramount concerns security privacy have come forefront. This paper presents a comprehensive framework for addressing multifaceted challenges privacy. Drawing on synthesis cutting-edge technologies, encryption methods, access control mechanisms, our approach aims fortify entire lifecycle. The delves into innovative strategies secure storage, transmission, processing, ensuring that sensitive information is shielded from unauthorized or malicious attacks. Additionally, incorporates robust privacy-preserving techniques, including anonymization differential privacy, uphold individual confidentiality. Through meticulous analysis current trends, emerging threats, regulatory landscapes, this not only provides theoretical but also practical guidelines seeking navigate intricate landscape while safeguarding integrity, security, vast datasets at their disposal.

Language: Английский

Citations

2