Predicting Occupant Behavior in Fully Automated Energy Communities

Background

Energy Communities (ECs) represent a paradigm shift in how we think about energy distribution and consumption. With the integration of smart grid technologies and advanced automation, ECs aim to enhance local energy efficiency, minimize costs, and boost renewable energy adoption. However, the effectiveness of these systems critically depends on human behaviour within such automated settings.

Current research indicates significant variability in automation acceptance and interaction among different user groups, directly impacting EC performance. This generates a thoughtful need to understand and predict how different types of occupants (supposedly EC members) will interact with automated energy systems.

This project addresses this challenge by developing a comprehensive framework for predicting occupant behaviour in automated ECs. Through the creation of EC-specific socio-behavioural archetypes, we aim to understand how different profiles engage with automation, identify potential barriers to adoption, allocate readiness and willingness of users and potential maturity as well as develop strategies to overcome challenges.

As part of a broader research initiative that combines behavioural design, HESS, and data analytics to create more effective and user-centric energy communities. Your research will highly influence the design and implementation of fully automated systems within ECs from a human centric perspective, ensuring alignment with user needs and preferences.

Thesis/Learning objectives

After the thesis has been performed the student should be able to:

• Develop EC-specific socio-behavioural archetype profiles

• Predict behavioural engagement with automation and uncovering barriers.

• Explore occupant interactions with automated systems to identify optimal design features.

Method of attack

Develop and administer a questionnaire to profile EC occupants and analyze their behavioral data using statistical and archetype-based frameworks. Simulate scenarios to forecast occupant reactions to automation, identifying socio-behavioral challenges and proposing targeted solutions. Additionally, create and validate a comprehensive measurement framework to assess generation metrics, consumption patterns, transaction behavior, and flexibility utilization effectively.

Proposed work condition and time schedule

The thesis is expected to start under January 2025 (wk. 3) and be completed in June 2025 (wk. 23). Intermediate reports will be due in early March (wk. 10) and late April (wk. 17).

Supervisor at KTH

Supervisor at EXP

Malek Anouti , Head of Behavior and Service Design