Memberships
PhD student Paul Westernmann successfully defended his thesis today with only editorial changes. Thanks Dr. David Bristow, Dr. Bryony DuPont and Dr. Nishant Mehta for examining. Check out Paul's impressive publication list here: Google Scholar
The Energy and Cities group has succefully obtained a grant from PICS with the City of Victoria to deliver effective climate mitigation and adaptation solutions for municipalities. The project has started April 2020 and will run for three years.
Using simulation to understand the behaviour of buildings and energy systems.
Future holistic, integrated energy systems solutions span from buildings (which are now active players in energy markets) to district and city-level designs and national scale infrastructure. Simulation is the sole means of exploring the performance of new designs and concepts in a rapidly changing techno-economic context; all buildings and systems are unique (there are no prototypes) and simulation can explore the influence of future contextual parameters (energy prices, warmer climates, upgraded technologies) on new designs.
Exploring design spaces by examining trade-offs between multiple objectives.
The design space of possible systems and their performance is vast and intricate, making it impossible to discover the best solutions by trial-and-error or by exhaustive evaluation of all options. Computational design optimization (e.g. multi-objective genetic algorithms and mixed-integer linear programming formulations) are powerful tools for finding high-performing designs and exploring their sensitivity, robustness and resilience.
Leveraging developments in machine learning to better explore systems and data.
The next steps in achieving real progress in computational design aids will encompass statistical emulation of complex models and hyper-heuristic optimisers that learn how to solve problems better. Statistical emulators (also called meta-modelling) use methods like neural networks to approximate detailed models that are too time-consuming to run directly. Hyper-heuristics involves “optimising the optimiser”, either in advance using training data or during an optimisation.
Associate Professor, Group Leader
PhD Student
PhD Student
PhD Student
M.Eng at IMT Mines Albi Carmaux (2019)
Research interests:
Technical Lead
Masters Student
Bachelor of Engineering from UVIC (2020)
Research Interests:
PhD Candidate in Civil Engineering
Research Software Developer
In his spare time, Bryan plays ice hockey, volunteers at the Victoria Humane Society because he loves animals, and enjoys a round of disc golf with his friends when he can. Bryan is always looking to learn new programming and system administration skills.
Project Coordinator
Postdoc
Masters Student
Postdoc
Postdoc
Post-doc
Post-Doc, former PhD student
Post-Doc
Post-doc
Post-Doc
Mohammad Haris Shamsi earned a Master of Science degree in Energy Technologies in 2016 under a dual-degree mobility program organised by the company KIC InnoEnergy from Instituto Superior Tecnico and Uppsala University. Haris is an electrical engineer with a specialization in energy engineering and management. Haris was awarded a PhD in 2020 under the supervision of Dr. James O’Donnell at University College Dublin. His research focused on the formulation of reduced-order models to estimate the integrated end-use demand. Over the course of his PhD research, Haris extensively collaborated in different projects that focused on urban building stock modeling, data-driven building energy modeling, PV system optimization for neighborhoods, development of a DESTEST framework and district scale energy systems modeling. His research interests include building energy modeling, grey-box models, data-driven models, machine learning, system identification and uncertainty analysis.
Master's Student
PhD Student
Education Background: - B.Tech, Mechanical Engineering, Delhi Technological University (India) - M.Eng, Energy Systems, University of Illinois at Urbana-Champaign (USA)
After completing his masters education, Rajeev worked at an energy efficiency consortium consisting of gas and electric utilities, followed by an operations role with a community solar administrator in the Northeast United States. Rajeev’s research is focused on exploring data-driven building energy solutions to reduce carbon emissions and energy consumption, thereby increasing their resilience to climate change. When not studying, Rajeev loves to photograph landscapes and wildlife, hike mountains, and play computer games when the former activities become undoable. Research Interests: - Renewable energy systems - Building energy modeling - Data analysis - Carbon emissions reduction
Master's Student
Educational background:
Research interests are:
MASc Student
Master's student
Bachelor’s Degree in Cognitive Systems: Computational Intelligence and Design at UBC (2015)
Research interests:
Master's Student
Master's Student
Co-op
Having background in Physics and Engineering, I am able to research and develop potential innovative solutions. Having worked with MBE machine in my PhD program, as a multi-disciplinary system, I am very experienced in ultra high vacuum technology, data acquisition and monitoring systems with a solid background in data analysis (LabView, Matlab, Python, Origin, Excel). I am very interested to deepen my knowledge in data science and machine learning, and I found Dr. Evans research group a decent place to achieve that.
Co-op
Cameron is a second year Electrical Engineering student at the University of Victoria. He joined the Energy in Cities team at Uvic for his first Co-op work term.
Co-op
Co-op
Co-op
Guillaume is a fourth year computer science student at the University of Victoria. He is joining the Energy in Cities team for his first Co-op and is very interested in learning more about machine learning.
Co-op
Gabe is entering his second year at the University of Victoria studying Computer Science and Philosophy. He is interested in Machine Learning and its applications to efficient and sustainable development.
Co-op
Mark is a 4th year computer science student at UVic, and is returning for his 3rd work term with Ralph’s team. He has worked in the past as a system administrator, software developer, and IT support for the group, and will continue these tasks in the new work term.
Co-op
Research interests:
Co-op
Research interests:
Co-op
Ben is a 2nd year electrical engineering student at UVic. This is his first co-op term on Ralph’s team. He will be working on system administration, development, and general IT support for the team. Research interests: - sustainable energy generation - machine learning - computer systems engineering
Co-op
Education Background: 2nd year Mechanical Engineering student at the University of Victoria
Research Interests: - Applications of neural networks - Robotics - 3D printing
Co-op
My educational background: - a second-year physics and astronomy student at the University of Waterloo. My research interests: - Data science - Sustainable transportation
Co-op
I currently study at the University of Waterloo and going into my third year starting in the summer. I’m in the Architectural Engineering class of 2023, which is actually the first year of our program!
Research interests 1. Sustainable building design 2. Designing disaster resistant buildings 3. The influence of architecture on psychology
Co-op
A second-year electrical engineering student in my first co-op.
My research interests: - Robotics, - Power Systems, and - Machine Learning
Work Study Student
Education: - Pursuing Masters in Computer Science from University of Victoria - Bachelor of Engineering in Computer Science from Anna University, India (2020)
Work experiences: - Teaching Assistant at University of Victoria – Software Evolution - Software Engineer – HCL Technologies, India (Oct 2020 – August 2021) - Academic Intern – HCL Technologies, India (Feb 2020 – August 2020)
Research interest: - Machine learning - Computer Networks - Software Engineering
Co-op Student
Masters student from Applied Data Science, specializing in mathematic modeling, machine learning, and software engineering, with added emphasis on algorithm and data structure knowledge.
Education: - Master of Engineering in Applied Data Science from University of Victoria
Work experiences: - Research Assistant at Anhui Province Key Laboratory of Smart Agricultural Technology and Equipment - Hefei, China (07/2019 – 06/2020) - Teaching Assistant at Anhui Agriculture University - Hefei, China (02/2019 – 06/2019)
Research interest: - Machine learning - Optimization problems - Data analysis - Pattern recognition
Co-op Student
Passion for environmental sustainability and reducing negative impacts on our climate.
Education: - 3rd Year Bachelor of Engineering Student from UVIC - Major in Software Engineering
Research interest: - Reducing Building Energy Use and Emissions - Energy systems modelling
Co-op Student
Passion for environmental sustainability and reducing negative impacts on our climate.
Education: - 3rd year Computer Science, engineering B.SC.
Research interest: - Machine Learning - Data pipeline architecture
Co-op Student
Marcus is a second-year undergraduate student at UVic, attending his first co-op work term. While pursuing a degree in Mechanical Engineering, he is also experienced with software development.
Research interest: - Building energy modeling - Machine learning
Work experience: - Okanagan Falls Irrigation District - - Serviced local water systems - - Tested and debugged computer systems
Work Study Student
Education: - Pursuing Masters in Computer Science from University of Victoria - Bachelor of Engineering in Computer Science, Sathyabama Institute of Science and Technology, India
Work experiences: - IOS Developer for ZohoShow – Presentation App, at Zoho Corporation, Chennai, India (08/2018 – 08/2021).
Research interest: - Computer Graphics - Software Engineering - Artificial Intelligence - Application Development
NSERC Student
Co-op Student
Guest researcher
PhD candidate at UFAL - Universidade Federal de Alagoas
Undergraduate Student
Undergraduate Student
Civil Engineering Program at UVic (In Progress)
Software Intern
Academic Interests:
Personal Projects:
Programming Intern
Currently completing a Computer Science degree at the University of Victoria
For a list of side-projects, see Grey’s GitHub
Interests:
Researcher
A fast and ituative way to design net-zero ready buildings
The Net-Zero Navigator platform will allow building designers to leverage advancements in machine-learning based “surrogate modelling” to drastically improve their workflow in finding high-performance building designs. It features a set of surrogate models of archetype buildings which can be explored using intuitive visualizations via a Web interface. Advanced users can access the underlying code in the cloud, to apply the process of surrogate modelling and visualization to their own building models.
The Net-Zero Navigator platform has two main interfaces: - Core: an interactive visualization interface to explore 30+ parameters for 16 archetype buildings and 20 climates across Canada - Advanced: easy-to-use Python scripts in Jupyter Notebooks that run in the cloud for modelers to apply surrogate modelling to their own building model.
Surrogate modelling fits a machine-learning model (we don’t call it AI, this isn’t SkyNet) over a set of samples from a simulation program, providing a fast ‘surrogate’ for the underlying detailed model. This paper provides a review of recent developments in this area.
Surrogate modelling provides a way to generate approximate solutions which are easily accurate enough for early-stage design, and incredibly fast to evaluate, without requiring a vast number of samples or a lot of time to fit the model. As an example of this, Figure 1 gives details of a substantial surrogate model, which has 32 parameters spanning geometry, materials, set points, ventilation and building systems. The plot compares the actual EnergyPlus results (x-axis) with the surrogate model result (y-axis), and gives some summary statistics like the R² score of 0.996 and the mean absolute percentage error (MAPE) of 3.65%. The model was fitted on 8,000 EnergyPlus samples (total run time ~ 24 hours on a 16 core machine). The surrogate model returns a result in 32 microseconds which is 7.5 million times faster than an EnergyPlus simulation, also meaning we can generate a million samples in 32 seconds. Our codebase is organised to make it easy to integrate the machine learning methods needed to build surrogate models with the parametric building energy models needed to generate the underlying samples.
This provides a way to generate approximate solutions which are easily accurate enough for early-stage design, and incredibly fast to evaluate, without requiring a vast number of samples or a lot of time to fit the model. As an example of this, Figure 1 gives details of a substantial surrogate model, which has 32 parameters spanning geometry, materials, set points, ventilation and building systems. The plot compares the actual
EnergyPlus results (x-axis) with the surrogate model result (y-axis), and gives some summary statistics like the R² score of 0.996 and the mean absolute percentage error (MAPE) of 3.65%. The model was fitted on 8,000 EnergyPlus samples (total run time ~ 24 hours on a 16 core machine). The surrogate model returns a result in 32 microseconds which is 7.5 million times faster than an EnergyPlus simulation, also meaning we can generate a million samples in 32 seconds. Our codebase is organised to make it easy to integrate the machine learning methods needed to build surrogate models with the parametric building energy models needed to generate the underlying samples.
Building and Energy Simulation, Optimization and Surrogate-modelling (funded by CANARIE).
The Building and Energy Simulation Optimization and Surrogate-modelling (BESOS) platform is a cloud-based portal that will make modular, reusable software components for integrated energy systems analysis available to researchers. Buildings, renewable energy generation and storage technologies and associated energy systems all pose complex, interacting design and operational challenges. Finding high-performing solutions to these problems requires a new generation of computational tools, blending aspects of simulation, optimization, machine learning and visualization.
The project is funded by a competitive grant from CANARIE.
The core BESOS modules will include:
BESOS modules will be accessible in various ways:
Research teams who will collaborate on developing components of the platform include:
Project is funded by Pacific Institute of Climate Solutions (PICS)
Together with our solutions partner the City of Victoria, we have obtained funding from 
Municipalities are at the forefront of the fight against climate change, but lack the tools and evidence to make effective policy decisions. The project will develop a simple and practical yet comprehensive and robust framework for analyzing and comparing municipality-level climate policies. It will encompass the main sources of carbon emissions (buildings, transport and energy). The framework will allow the City to identify and prioritise climate solutions that will meet the stringent obligations of its Climate Leadership Plan: to reducing greenhouse gas (GHG) emissions by 80% by 2050 (from a 2007 baseline). In 2016 buildings accounted for 51% of emissions (29% commercial, 22% residential), and offer the greatest opportunity to act. Options to reduce emissions include 100% renewable energy, all new buildings to be net-zero energy-ready, retrofitting of existing buildings, and promoting the uptake of electric vehicles and other modes of transport. This project will provide the City with evidence and analysis to inform future goals, such as “by 2030 the City requires X buildings of Y type be retrofitted using measures A, B and C, which will offer GHG reductions of X tonnes.”
The first step will be to implement a novel automated data pipeline to generate a high-resolution dataset by combining building-level information from BC Assessment, NRCan and other sources. This will be supported by energy simulations of specific building archetypes (selected based on type, age etc.), and calibration against measured energy use data for specific buildings. This will underpin detailed climate solutions pathways analysis of all building-related solutions, including energy efficiency and emission reduction retrofits, fuel switching (including electrification) and rapid adoption of the BC Energy Step Code for new buildings. The potential adaptation of buildings to rising temperatures to avoid increased energy use for cooling will also be examined, ensuring that the city can adapt climate change.
Other sources of emissions will be analysed in this project to give a fair basis for comparison of a portfolio of solutions. Transport is a key part of the remit of the City in reducing emissions, and this project will draw on data from other studies to incorporate these solutions into the framework, including provision for electric vehicle charging and for infrastructure to encourage cycling. It will also add solutions relating to the low-carbon supply of energy, for example to optimize between efficiency and fuel switching. This will include the need to adopt building-scale PV to contribute renewable electricity, the role of renewable natural gas, and possible limits on the current electricity grid infrastructure for electrification of heating and vehicles. The framework will be flexible and easily adaptable to accommodate new information, recognizing that policy development is an evolving process. Changes include population growth (the City of Victoria expects to accommodate 20,000 new residents by 2041), new technology uptake rates, changing prices for energy sources, decreasing costs of new technologies, and the subtleties of human behaviour.
Applying machine learning in building energy management systems (funded by an NSERC Engage Grant with SES Consulting.
The SmartEMS project will develop data analysis and machine learning approaches suitable for incorporation in non-residential building energy management systems, and test them in real buildings. Dramatic recent improvements in the power of machine learning have made it possible to train and deploy such algorithms to solve practical challenges. Complex energy systems in buildings present many such challenges, from set-point optimization to predictive control. SES Inc. has the capabilities and client-base to take advantage of this.
There are two core approaches: offline learning from data, and real-time predictive control. The former will identify underlying trends and areas of concern by analysis of operational data; the latter will develop and train machine learning controllers that will improve operation based on weather predictions. The two together can deliver a highly flexible, robust solution.
SmartEMS will use open-source systems and protocols (VOLTTRON, BACnet) that have been successfully used by SES on previous projects. Open-source state of the art machine learning libraries based in Python (scikit-learn, TensorFlow) will be used, along with other Python-based data analysis and visualisation libraries. Remotely accessible interface hardware (bare-bones PCs; Raspberry Pis) will be deployed in test buildings. Cloud computing from CANARIE will be used for computationally intensive parts of the process.
The output will be a commercially deployable solution based on the latest academic research; parts of this will also be released as open-source. This will form the basis for an ongoing collaboration. The concept has significant potential to improve energy use, emissions and comfort in commercial buildings.
Modular Optimization and Simulation of Energy Systems (funded by an NSERC Discovery Grant).
Preventing disastrous levels of climate change, ensuring energy security and achieving a sustainable future all require novel energy systems. These will be less centralised and ‘top-down’ since local balancing of demand and supply is critical temporally and spatially. Analysis of these systems must span from buildings (which are now active players in energy markets) to district, city and national infrastructure. The unique context of energy systems requires efficient, adaptable design tools able to quickly explore new areas and emerging problems. Two exciting new developments in machine learning (tuning of optimization algorithms using hyper-heuristics and efficient fitting of meta-models using statistical emulators) can be combined in a modular fashion to provide such tools.
This research program will investigate the holistic, integrated modelling, design and optimization of diverse energy systems. It will leverage the benefits of a modular modelling environment, encompassing simulation and analysis, optimization, hyper-heuristics and statistical meta-models amongst others. Existing simulation tools address single design options rather than extensive design-space exploration. There has been considerable success in applying computational optimization methods to find good solutions across a broad design-space, but further progress requires a different approach in which optimization and modelling are coupled more closely. The underlying methodology is the modularisation of simulation, optimization and meta-modelling elements to form a modular modelling environment. New and existing techniques will be combined more effectively, then applied to diverse energy systems problems with academic and commercial partners. The modularisation of optimization will allow the tuning of optimizers for particular sub-problems using hyper-heuristics (‘optimizing the optimizer’). Statistical meta-models will allow time-consuming simulations to be replaced by fast approximations which give adequate accuracy during the early stages of optimization. Models can be easily reused and reconfigured to address wide-ranging design problems to meet new research challenges. This flexibility will enable an adaptive process rather than the solution of a static problem. Extensions will cover semi-autonomous module configuration and expansion to additional domains such as city planning and electric vehicle deployment.
The impact of the research program will be to deliver more useful, more powerful, more holistic simulations and optimizations by embracing modularity. Faster, more detailed exploration of complex design-spaces will allow broader questions to be explored in greater depth. This will enable significant improvements in how energy systems for buildings, districts and cities can be designed and operated to meet future challenges.
Birdsell, B., Evins, R. 2022. A comparison of machine learning functions for time-series prediction in buildings eSim 2022.
This work undertakes a comprehensive comparison of RNNs and CNN-based ResNets for both multivariable day-ahead and annual predictions with specific focus on their application in buildings.
Ledee, F., Crawford, C., Evins, R. 2022. The influence of time horizon on energy hub sizing eSim 2022.
Sizing energy hubs with interdependent loads, energy sources and devices is a computationally intensive task requiring at least a year of hourly data per load and source.
Jowett-Lockwood, L., Evins, R. 2022. Using a Convolution Neural Network to Detemine the Thermal Characteristics of a Building eSim 2022.
Surrogate models are machine learning models that are trained using detailed simulation input and output data and can practically provide instant results.
Torabi, M., Evins, R. 2022. An LCA Framework to Prioritize Carbon-Senitive Measures in Residential Buiding Design eSim 2022.
Building design involves numerous trade-offs between several design objectives that span multiple aspects with diverse effects on building subsystems.
Kotha, R., Ledee, F., Shamsi, M., Evins, R. 2022. A clustering framework to identify non-residentia building archetypes using subsystem-level targeting eSim 2022.
With the proliferation of building energy management systems and smart meters, high-resolution time-series data have become more easily accessible.
Barton, R., Shamsi, M., Torabi, M., Evins, R. 2022. Modeling household energy retrofits through data-driven archetype formulation eSim 2022.
Existing buildings provide significant opportunities to reduce the share of the building sector on the overall energy consumption and greenhouse gas emissions.
Christiaanse, T. V., Loonen, R. C. G. M., Evins, R. 2021. Techno-economic optimization for grid-friendly rooftop PV systems - a case study in British Columbia. Sustainable Energy Technologies and Assessments. (47) 101320.
This paper combines a detailed PV array model and a building energy surrogate model with an energy hub optimization to maximise the profitability of a PV array by aligning generation with building demands.
Baasch G., Rousseau, G., Evins R. 2021. A conditional Generative Adversarial Network for energy use in multiple buildings using scarce data. Energy and AI. (5) 100087.
We explore the power of GANs (two neural networks that compete with each other) to generate synthetic time series of building energy use. We achieve satisfactory performance using limited input data, which is often a problem for GANs.
G Baasch, P Westermann, R Evins Identifying whole-building heat loss coefficient from heterogeneous sensor data: An empirical survey of gray and black box approaches (2021) Energy and Buildings 241, 110889
This paper benchmarks seven different methods for characterizing building heat loss by estimating the whole-building heat loss coefficient. It uses a large set of synthetic data generated using EnergyPlus simulations. The methods compared include gray box approaches (e.g. estimating parameters of RC networks) and novel black box approaches (e.g. neural networks).
A Rahimzadeh, TV Christiaanse, R Evins Optimal storage systems for residential energy systems in British Columbia (2021) Sustainable Energy Technologies and Assessments 45, 101108
We explore the changes in optimal storage system sizing for on-grid, off-grid and 100% renewable scenarios. In on-grid systems, the results show that even the cheapest energy storage system is not feasible with the current cost of grid electricity. For off-grid and 100% RE scenarios, we look at the performance and cost that storage would have to reach to play a role in such systems.
Bowley, W., Evins, R. 2021. Energy system optimization including carbon-negative technologies for a high-density mixed-use development. International Journal of Sustainable Energy Planning And Management. (31) 211–225.
This paper examines the optimal energy system for a high-density residential development using the energy hub framework, which was extended to include material streams biochar production, a carbon negative technology.
P Westermann, TV Christiaanse, W Beckett, P Kovacs, R Evins besos: Building and Energy Simulation, Optimization and Surrogate Modelling (2021) Journal of Open Source Software 6 (60), 2677
This paper describes the besos Python library along with the associated BESOS platform, which help researchers and practitioners explore energy use in buildings more effectively. This is achieved by providing an easy way of integrating many disparate aspects of building modelling, district modelling, optimization and machine learning into one common library.
P Westermann, R Evins Using Bayesian deep learning approaches for uncertainty-aware building energy surrogate models (2021) Energy and AI 3, 100039
In this paper, we train two types of surrogate models (dropout neural networks and stochastic variational Gaussian Process models) that provide estimates of model error alongside predictions of specific outputs. The surrogate model processes 35 building design parameters (inputs) to estimate 12 annual building energy performance metrics (outputs). We benchmark both approaches and show their accuracy to be competitive. Overall model errors can be reduced by up to 30% if 10% of samples with the highest uncertainty are replaced with values from the underlying high-fidelity model.
Westermann, P., Welzel, M., Evins, R. Using a deep temporal convolutional network as a building energy surrogate model that spans multiple climate zones (2020). Applied Energy (278) 115563.
In this study we use convolutional neural networks that process annual hourly weather files that consist of more than 150'000 values to predict building energy performance at any location in Canada in less than a second. This is a fast alternative to whole building energy simulation which provides performance estimates in minutes.
Bowley, W., Evins, R. Assessing energy and emissions savings for space conditioning, materials and transportation for a high-density mixed-use building. (2020). Journal of Building Engineering (31) 101386.
This paper explores the combined impact of building-related and transportation emissions in the context of avoiding urban sprawl. The proposed 'mothership' combines all the functions of a typical suburb into one super-high-density development, reducing both sources of emissions.
Westermann, P., Deb, C., Schlueter, A., Evins, R. (2020). Unsupervised learning of energy signatures to identify the heating system and building type using smart meter data. Applied Energy (264) 114715.
The study provides a method to automatically extract heating system and building type information from smart meter time series data only. The method relies on the concept of energy signatures.
Westermann, P., Evins, R. Surrogate modelling for sustainable building design – A review. (2019). Energy and Buildings (198) 170-186.This is a literature review summarising the most important works in the field of building energy surrogate models.
Forde, J., Hopfe, C., McLeod, R., Evins, R. (2019). Temporal optimization of affordable Passivhaus dwellings: is peak load a more reliable metric for cost optimal design? Applied Energy (261) 114383.
This paper applies a multi-objective optimisation approach to affordable Passivhaus delivery. One key finding is that reduced south facing glazing improves future resilience to overheating. Overalll, we demonstrate how multi-objective optimization facilitates evidence-based decision making.
A comparison of building energy optimization problems and mathematical test functions using static fitness landscape analysis. C. Waibel, G. Mavromatidis, R. Evins, J. Carmeliet, Journal of Building Performance Simulation, 2019.
Fitness Landscape Analysis is a very important but generally overlooked part of optimization and design space exploration. In this paper we explore the similarities between actual building energy optimization problems from the literature and the COCO testbed of mathematical test functions used in the field of computational optimization. We identify a large degree of variability between the landscapes of different building problems, but we are able to link clusters of problems to different test functions.
Surrogate modelling for sustainable building design - A review. P. Westermann, R. Evins, Energy and Buildings, 2019.
Surrogate models emulate an expensive high-fidelity building simulation model using statistical methods from machine learning. Once validated to approximate the detailed model well enough, a surrogate can be used to almost instantly predict the performance of a wide range of designs. This paper focuses on surrogates that predict aggregated design metrics (e.g. annual energy use) rather than time series data. We review 57 applications of surrogate modelling to sustainalbe building design, and analyse the modelling methods used, variables and outputs examined and the performance achieved. This information is summarized to serve as practical guide, making surrogate modelling accessible for future researchers.
Clustering and ranking based methods for selecting tuned search heuristic parameters. C. Waibel, R. Evins, J. Carmeliet. IEEE Congress on Evolutionary Computation, Wellington, New Zealand, 2019.
An architect goes amongst the computer scientists to talk about new methods for tuning the parameters of search heuristics! This paper presents two alternative methods for selecting tuned hyper-parameters of search heuristics for computationally expensive simulation-based optimization problems.
Co-simulation and optimization of building geometry and multi-energy systems: Interdependencies in energy supply, energy demand and solar potentials. C. Waibel, R. Evins, J. Carmeliet, Applied Energy, 2019.
This paper presents a co-simulation framework for the simultaneous optimization of building geometries and multi-energy systems using the energy hub approach, showing that this has significant benefits over optimizing each independently. The study shows that coupling multiple simulators into a common optimization and design workflow brings together architectural aspects, such as geometry, with engineering aspects, such as the energy system design, and microclimate conditions, such as local solar potentials. Thus, essential interdependencies between the energy supply and demand side can be captured in the design of energy efficient cities.
Building Energy Optimization: An Extensive Benchmark of Global Search Algorithms. C. Waibel, T. Wortmann, R. Evins, J. Carmeliet, Energy and Buildings, 2019.
We present an extensive benchmark of black-box optimization algorithms for a range of building energy simulation problems, the aim being to go beyond 'yet another algorithm' that is demonstrated for only one problem. Using established and newly proposed metrics for optimizer performance evaluation, we show that no single optimizer dominates benchmark for all metrics and/or problems. There is some impact of tuning hyper-parameters of optimizers to specific problem dimensions. Overall, RBFOpt is the best algorithm for a very small evaluation budget, but best results for high evaluation budgets are obtained with CMA-ES.
Decarbonizing the electricity grid: the impact on urban energy systems, distribution grids and district heating potential., B. Morvaj*, R. Evins & J. Carmeliet, Applied Energy, vol. 191, pp. 125–140,
This paper determines the impact on district energy systems (DES) of different levels of renewable energy share in the electricity grid using a model that integrates DES optimisation, linearised AC power flow and district heating design.
Optimization framework for distributed energy systems with integrated electrical grid constraints., B. Morvaj, R. Evins & J. Carmeliet, Applied Energy, vol. 171, pp. 296-313, 2016.
Broad energy systems research regards the electrical grid as an infinite resource when optimising building and district-level systems, whereas power systems research conducts detailed analysis of the electrical grid, but treats the system components, layout and operation as fixed. This work brings together these two domains by incorporating (linearised) power flow equations into the energy hub modelling framework, optimising the energy system holistically whilst accounting for the limitations of the electrical grid. This gave significantly different results, highlighting the importance of accounting for these constraints.
Variability between domestic buildings: the impact on energy use, R. Evins, K. Orehounig & V. Dorer, Journal of Building Performance Simulation, vol. 9(2), pp. 162-175, 2016.
There are many sources of variation between different buildings, including occupant presence and behaviour, lighting and appliance use and temperature preferences as well as physical properties like insulation and air tightness. These are of particular importance when analysing district energy systems, since the relative temporal alignment of the loads has a huge impact on the aggregated profiles. A statistical analysis was performed on these profiles to identify the greatest sources of variation, giving a better understanding of how district systems should account for this at the design stage.
Multi-level optimization of building design, energy system sizing and operation, R. Evins, Energy, vol. 90 II, pp. 1775-1789, 2015.
In order to explore the performance of different energy system designs, it is necessary to know how they will perform operationally; the more complex the system, the more detailed this operational simulation must be to capture the true behaviour. This work nests both a building energy simulation (EnergyPlus) and an operational scheduling problem (the energy hub model) within a wider design exploration (a multi-objective genetic algorithm) so that the three levels can be explored holistically, leveraging the benefits of different solvers at each level.
New formulations of the energy hub model to address operational constraints, R. Evins, K. Orehounig, V. Dorer & J. Carmeliet, Energy, vol. 73, pp. 387-398, 2014.
The energy hub concept that sits at the core of much of my recent work balances intermittent energy demands and supplies through an operational optimisation every timestep. It can be applied from building to city scale, and can inform the design of many types of multi-energy systems and networks. However, in the simplified forms used prior to this work, the model fails to account for many significant aspects of equipment performance like minimum loads, run times or startup frequencies. This work adds rigour by including many additional constraints regarding the way energy systems really function, making this popular method much more applicable to the analysis of real energy systems.
A review of computational optimisation methods applied to sustainable building design, R. Evins, Renewable and Sustainable Energy Reviews, vol. 22, pp.230-245, 2013.
This review summarises the current state of the field of building optimisation, analyses the trends in the rapid growth of the field, and critically addressed the gaps in the existing body of work. I commented on possible future directions that might be profitably explored, and gives opinion on the best ways that this could be achieved. This work has become very highly-cited as an overview of the progress and challenges in the field.
A case study exploring regulated energy use in domestic buildings using design-of-experiments and multi-objective optimisation., R. Evins, P. Pointer, R. Vaidyanathan & S. Burgess, Building and Environment, vol. 54, pp. 126–136, 2012.
This paper applied the broad findings of my doctoral research to address the optimisation of domestic buildings in the UK to meet the building regulations as cheaply as possible – a situation faced frequently by industry practitioners. It uses design-of-experiments and systems concepts to reduce the scale of the problem to make it computationally manageable, also critical for application in real practice. The underlying simulation process was encapsulated in a software tool that could be easily applied by design team members.
