Integrating Deep Learning and Energy Management Standards for Enhanced Solar–Hydrogen Systems: A Study Using MobileNetV2, InceptionV3, and ISO 50001:2018 DOI Creative Commons
Salaki Reynaldo Joshua,

Yang Junghyun,

Sanguk Park

et al.

Hydrogen, Journal Year: 2024, Volume and Issue: 5(4), P. 819 - 850

Published: Nov. 10, 2024

This study addresses the growing need for effective energy management solutions in university settings, with particular emphasis on solar–hydrogen systems. The study’s purpose is to explore integration of deep learning models, specifically MobileNetV2 and InceptionV3, enhancing fault detection capabilities AIoT-based environments, while also customizing ISO 50001:2018 standards align unique needs academic institutions. Our research employs comparative analysis two models terms their performance detecting solar panel defects assessing accuracy, loss values, computational efficiency. findings reveal that achieves 80% making it suitable resource-constrained InceptionV3 demonstrates superior accuracy 90% but requires more resources. concludes both offer distinct advantages based application scenarios, emphasizing importance balancing efficiency when selecting appropriate system management. highlights critical role continuous improvement leadership commitment successful implementation universities.

Language: Английский

AI-Driven Innovations in Building Energy Management Systems: A Review of Potential Applications and Energy Savings DOI Creative Commons

Dalia Mohammed Talat Ebrahim Ali,

Violeta Motuzienė, Rasa Džiugaitė-Tumėnienė

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(17), P. 4277 - 4277

Published: Aug. 27, 2024

Despite the tightening of energy performance standards for buildings in various countries and increased use efficient renewable technologies, it is clear that sector needs to change more rapidly meet Net Zero Emissions (NZE) scenario by 2050. One problems have been analyzed intensively recent years operation much than they were designed to. This problem, known as gap, found many often attributed poor management building systems. The application Artificial Intelligence (AI) Building Energy Management Systems (BEMS) has untapped potential address this problem lead sustainable buildings. paper reviews different AI-based models proposed applications with intention reduce consumption. It compares evaluated reviewed papers presenting accuracy error rates model identifies where greatest savings could be achieved, what extent. review showed offices (up 37%) when employ AI HVAC control optimization. In residential educational buildings, lower intelligence existing BEMS results smaller 23% 21%, respectively).

Language: Английский

Citations

13
Energy Intelligence: A Systematic Review of Artificial Intelligence for Energy Management DOI Creative Commons
Ashkan Safari, Mohammadreza Daneshvar, Amjad Anvari‐Moghaddam

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(23), P. 11112 - 11112

Published: Nov. 28, 2024

Artificial intelligence (AI) and machine learning (ML) can assist in the effective development of power system by improving reliability resilience. The rapid advancement AI ML is fundamentally transforming energy management systems (EMSs) across diverse industries, including areas such as prediction, fault detection, electricity markets, buildings, electric vehicles (EVs). Consequently, to form a complete resource for cognitive techniques, this review paper integrates findings from more than 200 scientific papers (45 reviews 155 research studies) addressing utilization EMSs its influence on sector. additionally investigates essential features smart grids, big data, their integration with EMS, emphasizing capacity improve efficiency reliability. Despite these advances, there are still additional challenges that remain, concerns regarding privacy integrating different systems, issues related scalability. finishes analyzing problems providing future perspectives ongoing use EMS.

Language: Английский

Citations

8
Adaptive Machine Learning for Automatic Load Optimization in Connected Smart Green Townhouses DOI Creative Commons
Seyed Morteza Moghimi, T. Aaron Gulliver,

T. Ilamparithi

et al.

Algorithms, Journal Year: 2025, Volume and Issue: 18(3), P. 132 - 132

Published: March 2, 2025

This paper presents an adaptive Machine Learning (ML)-based framework for automatic load optimization in Connected Smart Green Townhouses (CSGTs) The system dynamically optimizes consumption and transitions between grid-connected island modes. Automatic mode reduce the need manual changes, ensuring reliable operation. Actual occupancy, demand, weather, energy price data are used to manage loads which improves efficiency, cost savings, sustainability. An is employed that combines processing ML. A hybrid Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN) model analyze time series spatial data. Multi-Objective Particle Swarm Optimization (MOPSO) balance costs, carbon emissions, efficiency. results obtained show a 3–5% improvement efficiency 10–12% mode, as well 4–6% reduction emissions.

Language: Английский

Citations

0
Resource Optimization for Grid-Connected Smart Green Townhouses Using Deep Hybrid Machine Learning DOI Creative Commons
Seyed Morteza Moghimi, T. Aaron Gulliver,

T. Ilamparithi

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(23), P. 6201 - 6201

Published: Dec. 9, 2024

This paper examines Connected Smart Green Townhouses (CSGTs) as a modern residential building model in Burnaby, British Columbia (BC). incorporates wide range of sustainable materials and smart components such recycled insulation, Photovoltaic (PV) solar panels, meters, high-efficiency systems. The CSGTs operate grid-connected mode to balance on-site renewables with grid resources improve efficiency, cost-effectiveness, sustainability. Real datasets are used optimize resource consumption, including electricity, gas, water. Renewable Energy Sources (RESs), PV systems, integrated technology. creates an effective framework for managing energy consumption. accuracy, emissions, cost metrics evaluate CSGT performance. one four bedrooms investigated considering water systems party walls. A deep Machine Learning (ML) combining Long Short-Term Memory (LSTM) Convolutional Neural Network (CNN) is proposed the In particular, Mean Absolute Percentage Error (MAPE) below 5%, Root Square (RMSE) (MAE) within acceptable levels, R2 consistently above 0.85. outperforms other models Linear Regression (LR), CNN, LSTM, Random Forest (RF), Gradient Boosting (GB) all bedroom configurations.

Language: Английский

Citations

3
Load Optimization for Connected Modern Buildings Using Deep Hybrid Machine Learning in Island Mode DOI Creative Commons
Seyed Morteza Moghimi, T. Aaron Gulliver,

T. Ilamparithi

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(24), P. 6475 - 6475

Published: Dec. 23, 2024

This paper examines Connected Smart Green Buildings (CSGBs) in Burnaby, BC, Canada, with a focus on townhouses one to four bedrooms. The proposed model integrates sustainable materials and smart components such as recycled insulation, Photovoltaic (PV) solar panels, meters, high-efficiency systems. These elements improve energy efficiency promote sustainability. Operating island mode, CSGBs can function independently of the grid, providing resilience during power outages reducing reliance external sources. Real data electricity, gas, water consumption are used optimize load management under isolated conditions. Electric Vehicles (EVs) also considered system. They serve storage devices and, through Vehicle-to-Grid (V2G) technology, supply when needed. A hybrid Machine Learning (ML) combining Long Short-Term Memory (LSTM) Convolutional Neural Network (CNN) is performance. metrics include accuracy, efficiency, emissions, cost. performance was compared several well-known models including Linear Regression (LR), CNN, LSTM, Random Forest (RF), Gradient Boosting (GB), LSTM–CNN, results show that provides best results. For four-bedroom Townhouse (CSGT), Mean Absolute Percentage Error (MAPE) 4.43%, Root Square (RMSE) 3.49 kWh, (MAE) 3.06 R2 0.81. indicate robust optimization, particularly highlight potential for urban living.

Language: Английский

Citations

1
Architecture and Operational Control for Resilient Microgrids DOI
Alexandre F. M. Correia,

Miguel Cavaleiro,

Miguel Neves

et al.

Published: May 19, 2024

The increasing frequency of natural disasters has led to situations in which small urban centers and critical infrastructures become isolated from the main utility grid. microgrids' ability work autonomously grid presents a viable solution this problem. Microgrid resiliency is characteristic related capacity microgrid minimize impact disruptive events ensure that power supply maintained under variety adverse conditions. This especially important for such as hospitals, communications, computer networks military bases. objective paper simulate strategies propose an algorithm design management electric microgrids with focus on towards disaster situations. proposed solutions were validated, using experimental implemented at University Coimbra pilot. As result work, study efficiently manages loads microgrid, including automatic islanding operation, order increase its resilience when

Language: Английский

Citations

0
Integrating Deep Learning and Energy Management Standards for Enhanced Solar–Hydrogen Systems: A Study Using MobileNetV2, InceptionV3, and ISO 50001:2018 DOI Creative Commons
Salaki Reynaldo Joshua,

Yang Junghyun,

Sanguk Park

et al.

Hydrogen, Journal Year: 2024, Volume and Issue: 5(4), P. 819 - 850

Published: Nov. 10, 2024

This study addresses the growing need for effective energy management solutions in university settings, with particular emphasis on solar–hydrogen systems. The study’s purpose is to explore integration of deep learning models, specifically MobileNetV2 and InceptionV3, enhancing fault detection capabilities AIoT-based environments, while also customizing ISO 50001:2018 standards align unique needs academic institutions. Our research employs comparative analysis two models terms their performance detecting solar panel defects assessing accuracy, loss values, computational efficiency. findings reveal that achieves 80% making it suitable resource-constrained InceptionV3 demonstrates superior accuracy 90% but requires more resources. concludes both offer distinct advantages based application scenarios, emphasizing importance balancing efficiency when selecting appropriate system management. highlights critical role continuous improvement leadership commitment successful implementation universities.

Language: Английский

Citations

0