Background and Objectives
The ADRENALIN (Advanced Data Driven Energy services for Smart Buildings) project, initiated under the ERA-Net Smart Energy Systems Joint Call 2020, focused on enhancing energy efficiency and occupant comfort through big data analytics and machine learning.
The key objectives included:
- Development of a data sandbox with curated datasets from diverse international buildings.
- Organisation of data challenges on load disaggregation and HVAC control optimisation.
- Implementation and validation of winning solutions in real-world like settings.
- Creation of new business models for energy services.
- Dissemination of knowledge across the energy community.
Results Achieved
- Data Sandbox Development: A comprehensive collection of building-related data created a standardised environment crucial for algorithm development and benchmarking.
- Data Challenge Competitions: Two global competitions spurred innovation:
Load Disaggregation Challenge: Focused on algorithms to dissect total energy usage into specific end uses.
HVAC Control Optimisation Challenge: Utilised the BOPTEST framework to develop energy-efficient HVAC control strategies.
Key achievements include:
-Successful international competitions with academic and industry participation.
-Discovery of novel algorithmic approaches in energy management.
-Development of reproducible evaluation methodologies and open-source tools.
R&D Tasks
Key tasks conducted:
-Data collection and sandbox creation.
-Development of challenge frameworks and evaluation metrics.
-Comprehensive algorithm assessments.
-Planning for real-world solution implementations.
1. Load Disaggregation: Competition Insights and Data Analysis Potential
The outcomes of the load disaggregation competition are poised to serve as a foundational component for energy meter analysis within one of Kiona's solutions. This work highlights a significant potential for extracting valuable insights and identifying patterns within pre-existing data collections.
2. Smart Controls: Evaluation of Methodologies
While no direct, immediate commercial opportunities were identified from the smart controls segment of the initiative, the diverse methodologies explored provide a valuable indication of approaches that could be effective in specific scenarios and contexts.
3. BOPTEST: Application in Model Development and Feature Evaluation
The BOPTEST model demonstrates considerable potential for utilization in the training of existing operational models and in the process of testing and validating new features
4. Knowledge Transfer: Learnings from Competitor Presentations
The opportunity to observe presentations from various competitors and engage in Q&A sessions yielded valuable insights into their distinct approaches, methodologies, and the respective limitations of their solutions. This exchange has contributed to a broader understanding of the current landscape in these technological areas.
Buildings represent a high share of peak electricity demand, but thanks to their slow thermal inertia they also offer the potential to be one of the lowest-cost opportunities for providing the flexible demand needed to support increasing levels of variable renewable energy resources in electricity grids. To activate and scale this latent flexible demand opportunity, new data-driven software services are needed. ADRENALIN aims at facilitating large scale roll-out of data services and smart controls in the existing building stock. By collecting a large and varied pool of measurement data from real buildings (data sandbox), ADRENALIN will crowdsource to data challenge competitions the development of new algorithms. The best-performing solutions will be implemented in real-life conditions on the digital platforms of the partner companies to test their general validity and replicability, and to demonstrate real-life performance.
