FUEL-S RESEARCH

Engineering Sustainable, Intelligent & Resilient Communities

Integrating building energy modelling, artificial intelligence, renewable energy, field measurements, computational engineering and intelligent control to address real-world sustainability challenges.

Explore Our Research
OUR APPROACH

The FUEL-S Research Framework

FUEL-S combines real-world data collection, physics-based simulation, advanced computational techniques and intelligent control to develop practical pathways toward low-carbon and climate-resilient buildings and communities.

01

Real-World Data

Energy audits, field measurements, drone surveys, thermal imaging and geospatial information.

→
02

Digital Modelling

Validated building energy models, CFD simulations, digital archetypes and computational environments.

→
03

AI & Optimization

Machine learning, clustering, surrogate models, predictive analytics and optimization.

→
04

Real-World Solutions

Retrofit strategies, renewable energy integration, intelligent controls and resilient urban planning.

I Theme I
SUSTAINABLE BUILDINGS

Building Energy & Net-Zero Transitions

Developing data-driven methods to reduce building energy consumption, greenhouse gas emissions and fossil-fuel dependence through validated modelling, retrofits and renewable energy integration.

Theme I · Sub-theme i

Building Energy Modelling & Performance Optimization

EnergyPlus Energy Audits Retrofits Thermal Performance

Research focuses on evaluating and improving the energy performance of residential, commercial and community-scale buildings through calibrated energy models and measured building data.

The work combines energy audits, thermal performance assessment, building simulation, retrofit analysis and renewable energy strategies to support high-performance, low-carbon buildings.

OBJECTIVE Reduce energy demand while improving comfort, resilience and long-term building performance.
Theme I · Sub-theme ii

Net-Zero Energy Transitions in Agriculture

Agriculture Drone Surveys Thermal Imaging Renewable Energy

New Brunswick farms face high energy consumption, operational inefficiencies and continued dependence on fossil-fuel based energy systems.

This research develops a data-driven framework using energy audits, drone surveys, thermal imaging, calibrated EnergyPlus modelling, retrofit analysis and renewable energy integration to identify practical pathways toward farm-level net-zero energy.

The expected outcomes include reduced energy costs and greenhouse gas emissions, improved operational efficiency and greater resilience across agricultural facilities.

IMPACT A scalable pathway toward efficient, resilient and net-zero agricultural operations.
II Theme II
SOLAR & URBAN ENERGY

Intelligent Solar Energy & Urban Design

Combining AI, geospatial data and validated building archetypes to identify hidden renewable energy opportunities within cities and neighborhoods.

Theme II · Sub-theme i

AI-Driven Urban Solar Potential

Artificial Intelligence Solar Energy UAV Data GIS

Research focuses on unlocking the hidden solar energy potential of cities through artificial intelligence and intelligent energy modelling.

Real-time validated building archetypes are generated from drone and geospatial data to predict which buildings and neighborhoods provide the greatest active and passive solar potential.

These data-driven models support climate-resilient design, adaptive zoning, targeted retrofit strategies and more solar-efficient urban development.

VISION Smarter, greener and more solar-efficient cities.
Theme II · Sub-theme ii

Solar Neighborhood Planning

Urban Planning Solar Potential Building Archetypes Net-Zero

Urban form, building orientation, geometry, shading and neighborhood layout strongly influence both passive and active solar opportunities.

FUEL-S develops modelling and decision-making approaches that connect building-scale solar assessment with neighborhood-level planning and sustainable urban development.

APPLICATION Data-informed solar planning for buildings, neighborhoods and cities.
III Theme III
INTELLIGENT ENERGY SYSTEMS

Smart Energy, IoT & Control

Developing connected and intelligent energy management systems that combine simulation, machine learning, IoT technologies and real-time control.

Theme III · Sub-theme i

Intelligent Grid Load Management

Clustering Grid Control HVAC Demand Management

Research recreates real-world grid load-shedding scenarios within virtual simulation environments and develops clustering-based strategies for coordinated building energy control.

The objective is to reduce peak electrical demand while maintaining acceptable indoor conditions and distributing energy reduction across multiple buildings.

GOAL Flexible and coordinated energy management across building clusters.
Theme III · Sub-theme ii

IoT-Based Energy Control Platforms

IoT Sensors Cloud Integration Secure Systems

The research includes IoT-based product development for real-time data acquisition, system integration and physical control of distributed building energy systems.

A secure digital platform connects sensors, controllers, simulation models and cloud services to bridge virtual energy management strategies with real-world operation.

PLATFORM Simulation-to-reality integration for intelligent energy control.
IV Theme IV
CLIMATE RESILIENCE

Computational Engineering for Resilient Communities

Using advanced numerical simulations and data-driven surrogate models to understand environmental loads and improve the resilience of the built environment.

Theme IV · Sub-theme i

Extreme Wind Modelling in Urban Environments

CFD Extreme Winds Urban Geometry PEI Communities

Computational fluid dynamics models based on real Prince Edward Island neighborhoods are used to investigate the interaction between extreme wind events and the built environment.

The simulations provide detailed information about wind flow, pressure and localized environmental loading at the building and neighborhood scales.

APPLICATION Climate-resilient municipal and neighborhood design.
Theme IV · Sub-theme ii

Machine Learning Surrogate Models

Machine Learning Surrogate Modelling HPC Prediction

Machine learning models are developed from computational simulation data to provide rapid and accurate predictions without the computational cost of running full numerical simulations for every design scenario.

These models support faster design exploration, infrastructure assessment and climate-resilient municipal planning.

ADVANTAGE High-fidelity engineering predictions at substantially lower computational cost.
RESEARCH CAPABILITIES

Methods & Tools

An interdisciplinary toolkit connecting field measurements, numerical modelling and intelligent computational methods.

01

Building Energy Simulation

EnergyPlus-based modelling, calibration and performance analysis.

02

Drone & Geospatial Data

UAV surveys, photogrammetry and urban geometry acquisition.

03

Thermal Imaging

Building envelope assessment and thermal anomaly identification.

04

AI & Machine Learning

Predictive models, surrogate modelling, clustering and optimization.

05

Computational Fluid Dynamics

Numerical modelling of wind and environmental flow phenomena.

06

IoT & Intelligent Control

Connected sensing, real-time control and secure system integration.

07

Field Energy Audits

Real-world energy measurements and operational performance assessment.

08

High-Performance Computing

Computationally intensive engineering simulations and machine learning.

CURRENT RESEARCH

Selected Research Projects

Current FUEL-S research connects sustainable energy, computational engineering and intelligent systems with real-world communities and infrastructure.

NET-ZERO ENERGY ↗

Advancing Net-Zero Energy Transitions in New Brunswick's Agricultural Sector

Energy audits, thermal imaging, EnergyPlus modelling and renewable integration for agricultural facilities.

Explore Project
URBAN SOLAR ↗

AI-Driven Urban Solar Energy Potential

Validated building archetypes and geospatial intelligence for active and passive solar potential assessment.

Explore Project
SMART GRID ↗

Intelligent Building Cluster Load Management

Clustering, IoT and intelligent control strategies for coordinated building energy demand reduction.

Explore Project
CLIMATE RESILIENCE ↗

Extreme Wind Modelling & Machine Learning

CFD and machine learning methods for rapid climate-resilient urban and municipal design.

Explore Project
RESEARCH OUTPUT

Explore Our Publications

Discover journal articles, conference contributions, reports, patents and other scholarly work from FUEL-S.

View Publications →