{"title":"Q-GRID SMART: A blockchain-enabled smart home energy management and analytics system","authors":"Ameni Boumaiza","doi":"10.1016/j.rineng.2025.107093","DOIUrl":null,"url":null,"abstract":"<div><div>This study presents Q-GRID SMART, a decentralized, blockchain-enabled residential energy management platform integrating IoT-based monitoring, predictive analytics, and an interactive user dashboard. In a one-month pilot across 4,196 households in Doha, Qatar, machine learning models (GRU, Bi-LSTM) forecasted energy consumption, cost, and CO<sub>2</sub> emissions with RMSE = 160.9 kWh and MAE = 120.3 kWh. Post-deployment surveys (n = 312) indicated a Net Promoter Score of +42 and 87% reported improved energy awareness. The platform achieved an average 16.8% electricity reduction and 145.4 kg CO<sub>2</sub> savings per household per month. We further analyze how blockchain latency and confirmation times affect real-time control and user experience, proposing mitigation via edge control loops, batching, and Layer-2 solutions (state channels, rollups). These results demonstrate Q-GRID SMART's potential to deliver scalable, secure, and user-centric energy management solutions for utilities and households.</div></div>","PeriodicalId":36919,"journal":{"name":"Results in Engineering","volume":"28 ","pages":"Article 107093"},"PeriodicalIF":7.9000,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Results in Engineering","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2590123025031482","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
This study presents Q-GRID SMART, a decentralized, blockchain-enabled residential energy management platform integrating IoT-based monitoring, predictive analytics, and an interactive user dashboard. In a one-month pilot across 4,196 households in Doha, Qatar, machine learning models (GRU, Bi-LSTM) forecasted energy consumption, cost, and CO2 emissions with RMSE = 160.9 kWh and MAE = 120.3 kWh. Post-deployment surveys (n = 312) indicated a Net Promoter Score of +42 and 87% reported improved energy awareness. The platform achieved an average 16.8% electricity reduction and 145.4 kg CO2 savings per household per month. We further analyze how blockchain latency and confirmation times affect real-time control and user experience, proposing mitigation via edge control loops, batching, and Layer-2 solutions (state channels, rollups). These results demonstrate Q-GRID SMART's potential to deliver scalable, secure, and user-centric energy management solutions for utilities and households.