Load Optimization for Connected Modern Buildings Using Deep Hybrid Machine Learning in Island Mode

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

---

Harvesting sustainability: vertical agricultural greenhouses powered by renewable energy technologies

Energy Sources Part A Recovery Utilization and Environmental Effects, Journal Year: 2024, Volume and Issue: 46(1), P. 4688 - 4703

Published: March 27, 2024

This study investigates the practicality of integrating renewable energy systems to meet electricity needs a self-contained hydroponic greenhouse that functions as an environmentally friendly facility with reliable air conditioning and electrical infrastructure. The first step is assess greenhouse's annual consumption design system can sustain this year-round. results show daily between 0.75 2 kWh, thermal accounting for over 50% total consumption. To address issue, simulation model developed evaluate performance hybrid photovoltaic/wind connected electric storage battery optimize its integration into greenhouse. causes battery's voltage generally increase during charging (to 350.5 V) state charge change non-linearly depending on chemical makeup. An Energy Management System (EMS) then Hybrid Renewable (HRES), which works in two modes ensure balance uninterrupted power supply. economic environmental analysis three scenarios concludes are effective sustainable, estimated payback period approximately 6 8 years.

Language: Английский

---

Artificial Intelligence in Building Enclosure Performance Optimization: Frameworks, Methods, and Tools

Published: April 19, 2024

The design and specifications of a building enclosure can substantially impact the overall performance building. However, multifaceted nature dynamics environmental factors make it challenging to find optimal alternatives that meet criteria related thermal, daylighting, acoustics, indoor air quality performance. Artificial intelligence (AI) enables automation evaluation process, allowing for efficient synthesis information decision-making. Consequently, discipline architecture has readily assimilated AI computational optimization routines in process sustainable buildings. Specifically, advancements tools applications have facilitated use methods design. This chapter overviews frameworks, methods, used discussions focus on machine learning algorithms, specifically neural networks, as well including metaheuristic applied analysis envelope

Language: Английский

---

A Review of Bayesian Network for Fault Detection and Diagnosis: Practical Applications in Building Energy Systems

Published: Jan. 1, 2024

Language: Английский

---