Primary supervisor

Hao Wang

Households are becoming active participants in the energy system. In addition to consuming electricity, many now generate, store and manage energy through consumer energy resources (CERs), including rooftop solar, household batteries, electric vehicles, smart appliances and flexible loads. At the same time, smart electricity, gas and water meters—as well as appliance, weather and other contextual data—are creating new opportunities for artificial intelligence to understand and improve household energy use.

  • discovering household energy-use patterns, activities and behavioural changes;
  • forecasting electricity demand, solar generation, EV charging or other household energy activities;
  • detecting and disaggregating CERs, appliances and flexible loads from aggregate meter data;
  • identifying anomalies, equipment faults, electricity theft or unreliable meter measurements;
  • generating realistic synthetic energy data where real household data are limited or sensitive;
  • integrating electricity, gas, water, weather, tariff and socioeconomic data for multimodal energy analytics;
  • developing privacy-preserving, federated, explainable or fairness-aware AI for household energy applications;
  • using large language models or AI agents to simulate household behaviour, interpret energy data or provide personalised energy advice; and
  • supporting household energy management, demand flexibility and participation in virtual power plants and energy markets.

The specific research question will be tailored to the student’s background and interests. Students will work with real-world or realistically generated data and develop an AI-based method, evaluate it against suitable benchmarks, and investigate its implications for households, energy providers or the wider electricity system.

#sustainability

Aim/outline

This project aims to develop and evaluate AI methods for learning from household meter and energy data, with applications to understanding energy use, integrating CERs and enabling more intelligent, efficient and consumer-centred energy systems.

The project will typically involve:

  1. Selecting a household energy problem and relevant data, such as smart-meter demand, rooftop solar, battery, EV-charging, appliance, gas, water or contextual data.
  2. Analysing the data and formulating an appropriate prediction, detection, disaggregation, generation or decision-support task.
  3. Developing machine-learning, deep-learning, generative-AI or multimodal-learning methods.
  4. Evaluating model accuracy, robustness and generalisability, potentially alongside privacy, explainability, fairness or computational efficiency.
  5. Translating the results into insights for household energy management, CER integration, demand flexibility, energy programs or policy.

URLs/references

Some recent papers from the team (updated in Sep 2026).

1) Hao Wang, G Henri, CW Tan, R Rajagopal, Activity Detection And Modeling Using Smart Meter Data: Concept And Case Studies, 2020 IEEE Power & Energy Society General Meeting, 2020.

2) Zhuo Wei*, Hao Wang, Characterizing Residential Load Patterns by Household Demographic and Socioeconomic Factors, ACM e-Energy 2021 (The Twelfth ACM International Conference on Future Energy Systems), 2021.

3) Zhenyu Wang*, Hao Wang, Identifying the Relationship between Seasonal Variation in Residential Load and Socioeconomic Characteristics, ACM BuildSys 2021 (The 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation), 2021.

4) W Tang^, Hao Wang, XL Lee, HT Yang, Machine Learning Approach to Uncovering Residential Energy Consumption Patterns Based on Socioeconomic and Smart Meter Data, Energy, Vol. 240, pp. 1-11, 2022.

5) Cameron Martin*, F. Ke, Hao Wang, Non-Intrusive Load Monitoring for Feeder-Level EV Charging Detection: Sliding Window-based Approaches to Offline and Online Detection, IEEE EI2 2023 (The 7th IEEE Conference on Energy Internet and Energy System Integration), 2023.

6) X. Liang^, Hao Wang, Hybrid Transformer-RNN Architecture for Household Occupancy Detection Using Low-Resolution Smart Meter Data, The 49th Annual Conference of the IEEE Industrial Electronics Society (IEEE IECON), 2023.

7) F. Ke, Hao Wang, Divide-Conquer Transformer Learning for Predicting Electric Vehicle Charging Events Using Smart Meter Data, 2024 IEEE Power & Energy Society General Meeting (IEEE PESGM), 2024.

8) X. Liang^, Z. Wang*, Hao Wang, Synthetic Data Generation for Residential Load Patterns via Recurrent GAN and Ensemble Method, IEEE Transactions on Instrumentation and Measurement, 2024.

9) X. Wang, Hao Wang, B. Bhandari, L. Cheng, AI-Empowered Methods for Smart Energy Consumption: A Review of Load Forecasting, Anomaly Detection and Demand Response, IJPEM-Green Technology, 2024.

10) X. Chen^, C. Huang^, Y. Zhang, Hao Wang, Smart Energy Guardian: A Hybrid Deep Learning Model for Detecting Fraudulent PV Generation, The 10th IEEE International Smart Cities Conference (IEEE ISC2) 2024.

11) X. Chen^, C. Huang^, Y. Zhang, Hao Wang, Season-Independent PV Disaggregation Using Multi-Scale Net Load Temporal Feature Extraction and Weather Factor Fusion, The 8th IEEE Conference on Energy Internet and Energy System Integration (IEEE EI2) 2024.

12) X. Chen^, C. Huang^, Y. Zhang, Hao Wang, Privacy-Preserving Personalized Federated Learning for Distributed Photovoltaic Disaggregation under Statistical Heterogeneity, IEEE Transactions on Instrumentation and Measurement, 2025.

13) X. Liang^, Hao Wang, Learning and Generating Diverse Residential Load Patterns Using GAN with Weakly-Supervised Training and Weight Selection, IEEE Transactions on Consumer Electronics, 2025.

14) X Chen^, C Huang^, Y Zhang, Hao Wang, LoadGuard: An Adaptive Deep Learning Model for Smart Meter Electricity Theft Detection, The 23rd IEEE International Conference on Industrial Informatics (INDIN), 2025.

15) S Chetty^, HL Vu, Hao Wang, R Smyth, An LLM Framework for Inferring Household Energy Consumption Through Behaviour Simulation, ACM BuildSys 2025 (The 12th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation), 2025.

16) Y Bai^, X Liang^, C Huang^, J Zheng*, F Yang, Hao Wang, Machine Learning for Residential Energy Data Analytics Enhancing Energy Efficiency and Management: Datasets, Methods, and Applications, Current Sustainable/Renewable Energy Reports 13 (11), 1-17, 2026. (Invited Contribution)

17) J Zheng*, Hao Wang, Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights, The 10th IEEE Conference on Energy Internet and Energy System Integration (IEEE EI2) 2026.

18) J Zheng*, Hao Wang, Uncovering Residential PV-EV Co-Adoption from Smart-Meter Data: Load Archetypes and Detection for Demand-Side Planning, Next Energy, 2026.

(*Thesis students. ^HDR students.)

Required knowledge

Required: Python programming and an interest in artificial intelligence, data science or energy applications.

Preferred: Experience in machine learning, deep learning, data analytics or time-series analysis. Prior knowledge of energy systems is helpful but not essential.