This thesis introduces TreeC, a novel machine learning method for energy management in residential systems, aiming to reduce consumption and synchronize with low-emission energy production. TreeC demonstrates competitive performance against methods like model predictive control and reinforcement learning, offering improved transparency through understandable strategies. A real-world experiment revealed that TreeC and model predictive control performed worse than in simulations due to data limitations, highlighting the importance of hardware validation. The research also found that while energy management algorithms can reduce costs in electrified Belgian dwellings, these savings do not yet consistently outweigh implementation expenses. AI
IMPACT This research could lead to more efficient and transparent energy management systems in homes, potentially reducing costs and supporting renewable energy integration.
RANK_REASON The cluster contains an academic paper detailing a new method. [lever_c_demoted from research: ic=1 ai=0.7]
Read on arXiv cs.NE (Neural & Evolutionary) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →