Solar–Hydrogen Storage System: Architecture and Integration Design of University Energy Management Systems

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(11), P. 4376 - 4376

Published: May 22, 2024

As a case study on sustainable energy use in educational institutions, this examines the design and integration of solar–hydrogen storage system within management framework Kangwon National University’s Samcheok Campus. This paper provides an extensive analysis architecture integrated such system, which is necessary given increasing focus renewable sources requirement for effective management. starts with survey literature hydrogen techniques, solar technologies, current university systems. In order to pinpoint areas need improvement chances progress, it also looks at earlier research study’s methodology describes architecture, includes fuel cell integration, electrolysis production, harvesting, storage, customized needs university. explores consumption characteristics Campus University recommendations scalability scale suggested by designing three systems microgrids EMS Optimization solar–hydrogen, hybrid storage. To guarantee safe functioning, control strategies safety considerations are covered. Prototype creation, testing, validation all part implementation process, ends thorough system’s into university’s grid. The effectiveness its effect campus patterns, financial sustainability, comparisons conventional assessed findings discussion section. Problems that arise during addressed along fixes, directions further research—such as issues technology developments—are indicated. sheds important light viability efficiency academic environments, particularly regard accomplishing objectives.

Language: Английский

---

Integrated Battery and Hydrogen Energy Storage for Enhanced Grid Power Savings and Green Hydrogen Utilization

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(17), P. 7631 - 7631

Published: Aug. 29, 2024

This study explores the integration and optimization of battery energy storage systems (BESSs) hydrogen (HESSs) within an management system (EMS), using Kangwon National University’s Samcheok campus as a case study. research focuses on designing BESSs HESSs with specific technical specifications, such capacities power ratings, their into EMS. By employing MATLAB-based simulations, this analyzes dynamics, grid interactions, load strategies under various operational scenarios. Real-time data from are utilized to examine consumption, renewable generation, fluctuations, pricing providing key insights for optimization. finds that BESS manages fluctuations between 0.5 kWh 3.7 over 24 h period, remaining close 4 W extended periods. Grid fluctuates −5 kW 75 kW, while prices range 120 USD/kWh, peaking at 111 USD/kWh. Hydrogen varies 1 8 kWh, ranging −40 40 kW. Load keeps stable around 35 PV peaks 48 by 10th h. The findings highlight effectively manage distribution storage, improving efficiency, reducing costs approximately 15%, enhancing stability 20%. underscores potential in stabilizing operations integrating energy. Future directions include advancements technologies, enhanced EMS capabilities through artificial intelligence machine learning, development smart infrastructures. Policy recommendations stress importance regulatory support stakeholder collaboration drive innovation scale deployment, ensuring sustainable future.

Language: Английский

---

A Hybrid Machine Learning Approach: Analyzing Energy Potential and Designing Solar Fault Detection for an AIoT-Based Solar–Hydrogen System in a University Setting

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(18), P. 8573 - 8573

Published: Sept. 23, 2024

This research aims to optimize the solar–hydrogen energy system at Kangwon National University’s Samcheok campus by leveraging integration of artificial intelligence (AI), Internet Things (IoT), and machine learning. The primary objective is enhance efficiency reliability renewable through predictive modeling advanced fault detection techniques. Key elements methodology include data collection from solar production systems, potential analysis using Transformer models, identification in panels CNN ResNet-50 architectures. model was evaluated metrics such as Mean Absolute Error (MAE), Squared (MSE), an additional variation MAE (MAE2). Known for its ability detect intricate time series patterns, exhibited solid performance, with MAE2 results reflecting consistent average errors, while MSE pointed areas larger deviations requiring improvement. In detection, outperformed VGG-16, achieving 85% accuracy a 42% loss, opposed VGG-16’s 80% 78% loss. indicates that more adept detecting classifying complex faults panels, although further refinement needed reduce error rates. study demonstrates AI IoT particularly within academic institutions, improve management reliability. Results suggest enhances accuracy, provides valuable insights strategic output forecasting. Future could focus on incorporating real-time environmental prediction developing automated AIoT-based monitoring systems need human intervention. critical into advancing sustainability supporting growth AI-driven solutions university settings.

Language: Английский

---

Energy management in university campuses

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

---

Solar Panel Fault Detection: Applying Convolutional Neural Network for Advanced Fault Detection in Solar-Hydrogen System at University

Published: July 1, 2024

Language: Английский

---

AI-Driven Green Campus: Solar Panel Fault Detection Using ResNet-50 for Solar-Hydrogen System in Universities

Published: July 1, 2024

Language: Английский

---

Electricity Generation From Food Waste Using IOT

Published: May 3, 2024

Language: Английский

---

Integrating Deep Learning and Energy Management Standards for Enhanced Solar–Hydrogen Systems: A Study Using MobileNetV2, InceptionV3, and ISO 50001:2018

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

---

Optimizing energy dispatch strategies for hydrogen-based hybrid systems to address the camel-duck shape of electricity demand with increasing solar photovoltaic penetration

International Journal of Hydrogen Energy, Journal Year: 2024, Volume and Issue: 110, P. 1 - 31

Published: March 1, 2024

Language: Английский

---