The Research Group on Behavioural Energy Analytics & Modelling (BEAM) focuses on the adoption of digital technologies in energy ecosystems, addressing the overall global challenge of the energy transition and climate change. Digital technologies enhance the efficiency and reliability of energy production, distribution, and consumption, significantly reducing greenhouse gas emissions. Understanding the complex interactions between user behaviour and the wider system behaviour is crucial for optimising energy solutions, as it ensures that technological advancements align with behavioural practices and preferences, ultimately driving more sustainable energy consumption patterns.

We are based in QUT’s School of Information Systems and aim to become a globally leading research group addressing the complex and interdisciplinary field of energy informatics with a focus on behavioural challenges of the energy transition. Our group draws on various fields including information systems, behavioural economics, operations research, computer science, urban planning, management, psychology, and other disciplines. Our main objective is to develop novel solutions to improve our understanding of user behaviour for sustainable energy practices, enhance system behaviour for energy policy innovation, and leverage behavioural energy analytics and modelling to support decision-making, ultimately fostering a holistic and efficient energy ecosystem.

User Behaviour

At the micro level, we analyse user behaviour from a residential and industrial perspective to identify patterns and factors influencing energy consumption, understand the adoption and impact of renewable energy technologies, and assess responses to pricing and incentive programs. This analysis helps develop targeted interventions, promote sustainable energy practices, and enhance the effectiveness of demand-side management strategies. We address topics including but not limited to the following:

• Technology adoption: Decisions to adopt energy-efficient appliances, smart home technologies, or renewable energy sources (like solar panels) affect consumption and generation patterns.
• Behavioural change: Daily routines, habits, and preferences dictate when and how much energy is consumed. Awareness campaigns and education can lead to more energy-conscious behaviour, such as reducing energy consumption or shifting usage to off-peak times.
• Response to incentives: Consumers react to price signals, incentives, or regulations, such as time-of-use pricing, demand response programs, or subsidies for renewable energy adoption.

System Behaviour

At the macro level, we analyse system behaviour to understand the aggregate impacts of individual actions, optimise the balance between energy supply and demand, enhance grid stability, and improve the integration of renewable energy sources. This analysis helps identify systemic inefficiencies, predict future trends, and inform policy and infrastructure development to create a more resilient and sustainable energy ecosystem. We address topics including but not limited to the following:

• Energy supply and demand balance: Energy prices, availability of resources, and regulatory frameworks shape the energy market and influence system operations. The system needs to balance supply and demand in real-time, managing fluctuations caused by variable renewable energy sources and changing consumption patterns.
• Infrastructure and grid management: The efficiency and capacity of the grid infrastructure affect its ability to handle loads, integrate renewable sources, and respond to demand changes.
• Technological integration: Implementation of smart grids, storage solutions, and advanced analytics enables better prediction, control, and optimization of energy flows.

Behavioural Energy Analytics & Modelling

Analysing the interaction between user and system behaviour is crucial for understanding the dynamic and reciprocal relationships within the energy ecosystem. Collective user behaviour impacts system operations, while system conditions and policies influence households and organisations. By employing behavioural energy analytics and modelling, we identify emergent patterns and feedback loops. We aim to advance knowledge in areas including but not limited to the following:

• Diagnostic analytics: Why did this happen? To uncover underlying factors, we employ structural equation modelling to identify latent variables that influence energy behaviour, such as environmental attitudes, financial incentives, and comfort preferences. Further, we use analysis of variance to examine differences in energy usage, e.g., across demographic groups such as age and income level.
• Predictive analytics: What is likely to happen? We combine regression analysis with machine learning models to predict demand patterns, using variables such as weather conditions, appliance usage, and energy consumption data.
• Prescriptive analytics: What should we do? We design prescriptive strategies with mixed-integer linear programming and system dynamics modelling to simulate different scenarios of consumer behavioural changes and their effects on energy consumption.