Energy intelligence & NILM
Appliance-level energy modelling, compressor degradation, cold-load validation, load disaggregation, and energy feedback systems.
Visit Comp-Sust Lab →Energy Intelligence · Digital Supply Chains · Open Data · Applied AI
Prof. Stephen Makonin, PEng
Researcher, professional engineer, editor, and data-systems leader building practical AI and data infrastructure for energy, digital supply chains, sustainability, and reproducible science.
60+
peer-reviewed publications
3,000+
Google Scholar citations
4+
major public energy datasets
1
granted U.S. patent
Citation snapshot should be updated manually from Google Scholar before publishing.
About
Research leadership for data-intensive sustainability systems.
Dr. Stephen Makonin is an Adjunct Professor in the School of Engineering Science at Simon Fraser University and a professional engineer with deep experience in energy data analytics, non-intrusive load monitoring, public datasets, software systems, digital supply-chain intelligence, and applied machine learning.
His work connects research, engineering, and data governance: from appliance-level energy intelligence and open benchmark datasets to digital supply-chain decision support, editorial leadership, metadata standards, and practical AI systems for high-impact domains.
Research themes
Current areas of work
Open datasets & reproducibility
Public energy datasets, data descriptions, metadata quality, benchmarking, and reusable scientific data infrastructure.
Visit IEEE Data Descriptions →Applied AI & data governance
Responsible AI workflows, operational analytics, common data models, privacy-aware data sharing, supply-chain data governance, and data standards.
Visit SFU Big Data Hub →Digital Supply Chain Lab
Research and partner-facing work on supply-chain data sharing, disruption impact modelling, trusted operational data, and AI-enabled logistics decision support.
Visit DSCL →EV charging behaviour
Charging-session datasets, parking-lot usage efficiency, adoption modelling, infrastructure planning, and grid impacts.
Brain-signal modelling
EEG and BCI data modelling, activity classification, privacy-aware neurodata, and interpretable signal-analysis pipelines.
Selected publications
Representative work
2021
TraceGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks
IEEE Transactions on Smart Grid. Generative modelling for synthetic appliance-level energy signatures and NILM data augmentation.
2016
Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring
IEEE Transactions on Smart Grid. Sparse super-state HMM methods for practical real-time non-intrusive load monitoring.
2016
Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014
Scientific Data. The AMPds2 dataset, a widely used benchmark for energy-disaggregation and eco-feedback research.
2015
Nonintrusive Load Monitoring Performance Evaluation
Energy Efficiency. A concise framework for evaluating NILM and energy-disaggregation performance.
Datasets & software
Open infrastructure for energy and data research
AMPds
Appliance-level electricity, water, and natural gas data for load disaggregation and eco-feedback research.
RAE
Rainforest Automation Energy dataset for residential smart-grid meter data analysis.
HUE
Hourly Usage of Energy dataset for buildings in British Columbia.
GitHub
Research code, website source, and software projects.
Leadership & service
Editorial, standards, and professional contributions.
Founding Editor-in-Chief, IEEE Data Descriptions
Leading a gold open-access journal focused on high-quality, reusable, well-described engineering datasets.
Director, Digital Supply Chain Lab
Advancing applied research on supply-chain data infrastructure, resilience, partner engagement, and responsible AI-enabled decision support.
Vice-Chair, Big Data Governance & Metadata Management Working Group
Supporting standards work for metadata, data governance, and reusable data infrastructure.
IEEE, EGBC, SCC, and research community roles
Contributing to engineering practice, data standards, open science, and interdisciplinary research communities.
Contact
Connect with Stephen
For research collaboration, editorial service, data standards, consulting, or student supervision inquiries.