Smart integrated aquaponics system: Hybrid solar-hydro energy with deep learning forecasting for optimized energy management in aquaculture and hydroponics

IF 4.4 2区 工程技术 Q2 ENERGY & FUELS
Tresna Dewi , Pola Risma , Yurni Oktarina , Suci Dwijayanti , Elsa Nurul Mardiyati , Adelia Br Sianipar , Dzaki Rafif Hibrizi , M. Sayid Azhar , Dini Linarti
{"title":"Smart integrated aquaponics system: Hybrid solar-hydro energy with deep learning forecasting for optimized energy management in aquaculture and hydroponics","authors":"Tresna Dewi ,&nbsp;Pola Risma ,&nbsp;Yurni Oktarina ,&nbsp;Suci Dwijayanti ,&nbsp;Elsa Nurul Mardiyati ,&nbsp;Adelia Br Sianipar ,&nbsp;Dzaki Rafif Hibrizi ,&nbsp;M. Sayid Azhar ,&nbsp;Dini Linarti","doi":"10.1016/j.esd.2025.101683","DOIUrl":null,"url":null,"abstract":"<div><div>The global pursuit of sustainable energy and food production has led to the creation of integrated systems that maximize efficiency and minimize environmental impact. This research introduces the Smart Integrated Aquaponics System, combining hybrid solar-hydro energy with AI-driven forecasting and IoT-based monitoring to optimize aquaponics. By harnessing renewable energy and artificial intelligence, the system addresses challenges such as energy variability, resource efficiency, and scalability, particularly relevant to urban farming in land-scarce regions like Indonesia. The system integrates photovoltaic (PV) and micro-hydro sources with a hybrid energy management system for uninterrupted power. A long short-term memory recurrent neural network (LSTM-RNN) ensures precise energy forecasting, achieving mean absolute errors of 0.0579 for voltage and 0.1109 for power output. IoT sensors and convolutional neural networks (CNNs) monitor fish health and plant growth, providing accurate resource management and scalability. Experimental results highlight its effectiveness: solar irradiance peaked at 1200 W/m<sup>2</sup>, while micro-hydro turbines maintained stable power. Water treatment reduced turbidity below 10 NTU and total dissolved solids to 50 ppm, ensuring optimal water quality. Fish growth classification confidence ranged from 0.92 to 0.95, while plant monitoring accurately tracked development. Challenges remain, including seasonal energy variability and scalability. Enhancing energy storage, improving forecasting, and streamlining integration can address these issues. This research sets a benchmark for sustainable agriculture by demonstrating how hybrid energy systems, AI, and IoT can create scalable, efficient, and eco-friendly solutions, advancing global food and energy security.</div></div>","PeriodicalId":49209,"journal":{"name":"Energy for Sustainable Development","volume":"85 ","pages":"Article 101683"},"PeriodicalIF":4.4000,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy for Sustainable Development","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S097308262500033X","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

Abstract

The global pursuit of sustainable energy and food production has led to the creation of integrated systems that maximize efficiency and minimize environmental impact. This research introduces the Smart Integrated Aquaponics System, combining hybrid solar-hydro energy with AI-driven forecasting and IoT-based monitoring to optimize aquaponics. By harnessing renewable energy and artificial intelligence, the system addresses challenges such as energy variability, resource efficiency, and scalability, particularly relevant to urban farming in land-scarce regions like Indonesia. The system integrates photovoltaic (PV) and micro-hydro sources with a hybrid energy management system for uninterrupted power. A long short-term memory recurrent neural network (LSTM-RNN) ensures precise energy forecasting, achieving mean absolute errors of 0.0579 for voltage and 0.1109 for power output. IoT sensors and convolutional neural networks (CNNs) monitor fish health and plant growth, providing accurate resource management and scalability. Experimental results highlight its effectiveness: solar irradiance peaked at 1200 W/m2, while micro-hydro turbines maintained stable power. Water treatment reduced turbidity below 10 NTU and total dissolved solids to 50 ppm, ensuring optimal water quality. Fish growth classification confidence ranged from 0.92 to 0.95, while plant monitoring accurately tracked development. Challenges remain, including seasonal energy variability and scalability. Enhancing energy storage, improving forecasting, and streamlining integration can address these issues. This research sets a benchmark for sustainable agriculture by demonstrating how hybrid energy systems, AI, and IoT can create scalable, efficient, and eco-friendly solutions, advancing global food and energy security.
求助全文
约1分钟内获得全文 求助全文
来源期刊
Energy for Sustainable Development
Energy for Sustainable Development ENERGY & FUELS-ENERGY & FUELS
CiteScore
8.10
自引率
9.10%
发文量
187
审稿时长
6-12 weeks
期刊介绍: Published on behalf of the International Energy Initiative, Energy for Sustainable Development is the journal for decision makers, managers, consultants, policy makers, planners and researchers in both government and non-government organizations. It publishes original research and reviews about energy in developing countries, sustainable development, energy resources, technologies, policies and interactions.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信