AI & ML
Comfort energy management system for electrified buildings using hydrogen for seasonal storage
arXiv cs.SY0 views
arXiv:2511.04293v2 Announce Type: replace Abstract: Flexible loads and integrated energy storage in electrified buildings can align volatile renewable energy use with consumption. While battery energy storage systems provide short-term flexibility, hydrogen storage enables seasonal energy shifting. However, since hydrogen systems are expensive, coupling a fuel cell with a heat pump can reduce the required size of the hydrogen system and, therefore, investment costs. To fully exploit the flexibility of this integrated energy system, advanced control strategies are needed. This study proposes a comfort-oriented and grid-aware energy management system for an electrified building equipped with photovoltaics, a battery energy storage system, a hydrogen system, a heat pump, and domestic hot water storage. A novel fuzzy logic-based controller coordinates fuel cell and heat pump operation while exploiting building thermal mass as a flexibility resource. The proposed approach bridges the gap between simple rule-based control and model predictive control, enabling adaptive operation without system models, weather and demand forecasts, or high computational effort. The controller is evaluated over twelve winter weeks for a German single-family household and benchmarked against a rule-based controller and an ideal-forecast model predictive controller. Results show improved thermal comfort and lower electricity costs compared to the rule-based controller. Compared to model predictive control, the proposed controller reduces fuel cell operating hours and toggling counts, leading to more practical system operation. Overall, the proposed controller achieves a favorable trade-off between control performance and implementation complexity, combining low information requirements with improved comfort, storage use, and coordinated fuel cell-heat pump operation.
Source:https://arxiv.org/abs/2511.04293PreviousThe Ces\`aro Value IterationNextReal-Time Control of Sustainable Data Centers: A Two-Layer Model Predictive Control Framework with Workload Flexibility and Heat Recovery
Related posts
If you can't explain something in simple terms, you don't understand it (2017)
0Hacker News
The AI free tier is shrinking: five tools that changed pricing in 2026
0dev.to

Hyphen vs En Dash vs Em Dash: Differences, Examples, and When to Use Each
0dev.to
Running Whisper in the browser: 5 decisions behind a no-upload, no-cap transcriber
0dev.to

Mastering Agentic KV Caching: How to Slash LLM Agent Latency and Costs
0dev.to
![Robot Foundation Models and VLA — Ch.03: Vision Language Models for Robotics [EN]](https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fmezw012qznfr1y0dyk0f.png)
Robot Foundation Models and VLA — Ch.03: Vision Language Models for Robotics [EN]
0dev.to