# AI orchestration in ABB BuildingPro

## **Introduction**

The growing integration of AI technologies into building management — such as Reinforcement Learning (RL), Forecasting, and Large Language Models (LLMs) — opens up entirely new possibilities for efficiency, comfort, and sustainability. For these individual components not to run side by side in isolation, but to work together optimally, a central orchestration layer is needed.\
In Eliona, **rule chains** they take on exactly this role: they function as a visual, flexible, and extensible **AI orchestration tool**, connecting data, models, and actions into seamless, intelligent workflows.

## **Rule chains as an orchestration hub**

Rule chains are not just classic automation logic — they form the **central control and integration layer** for all AI modules in Eliona.\
This allows you to:

* **trigger AI models** (e.g., update forecasts, start/stop RL optimizations).
* **dynamically link data sources** (live sensor data, historical data, forecasts, external APIs).
* **implement decision logic** (conditions, prioritizations, escalations).
* **execute actions** (plant control, ticket creation, email sending, app interactions).

## **Examples of AI orchestration**

### **1. Peak load avoidance with forecast integration**

<figure><img src="https://content.gitbook.com/content/Nyvwhz1kEMXcHf4HLuZ8/blobs/HqKLyHe81JdOAfUKAMlo/forecast%20app%20(7).png" alt=""><figcaption></figcaption></figure>

* **Data sources**: Current load values + forecast attributes from the Forecast app.
* **Rule chain**:
  1. Get Data Node reads the predicted peak load.
  2. Condition Node checks whether the forecast value is > 200 kW.
  3. Action Node reduces the supply temperature or shifts consumer loads.
  4. Optional: Email Node proactively informs the energy team.
* **Result**: Peak loads are avoided before they occur.

### **2. Orchestrating Reinforcement Learning**

* **Trigger**: Forecast data or external events (e.g., tariff change).
* **Rule chain**:
  1. Condition Node checks whether there is optimization potential.
  2. RL Node starts or pauses the RL agent.
  3. Script Node evaluates performance and automatically creates reports.
  4. **Fail-safe monitoring**: An additional Condition Node continuously monitors whether the running RL model is performing unauthorized or safety-critical actions (e.g., exceeding comfort limits, impermissible switching frequency).
  5. If a violation is detected, an Action Node immediately sends a **stop signal** to the RL Node and, optionally, an alarm message to the operations team.
* **Result**: RL is only activated live when it brings maximum benefit — and can be both **automatically paused** and **stopped immediately** if it performs unwanted actions.

### **3. LLM-supported automation workflows**

#### **a) Rule chain via text prompt**

* **Use case**: With an LLM Node, complete rule chains can be created using simple text input.
* **Example prompt**:\
  \&#xNAN;*“Create a rule chain that reduces the supply temperature by 2 K when grid peaks exceed 200 kW and creates a ticket for the energy manager.”*
* **Result**: The LLM translates the prompt into a visual chain with Get Data, Condition, RL Node, and Action Node.

#### **b) Agent Node for ticket & email flows**

* **Ticket automation**: In the event of an alarm, the Agent Node uses the LLM to generate a complete ticket text, assigns the correct service technician, and stores priority as well as context.
* **Email recommendation**: When a critical deviation is detected, the Agent Node drafts an email with recommended actions\
  \&#xNAN;*("Please increase heating by 1 K until outdoor temperature > 15 °C")*\
  and sends it to the responsible department.

#### **c) Practical example: Autonomous AI optimizer**

1. **LLM Node**: *“Optimize energy in building A, maintain a 22 °C comfort window.”*
2. **Get Data Nodes**: Read current sensor values, forecast data, and tariff information.
3. **Correlation Script Node**: Identifies relevant influencing factors (e.g., outdoor vs. indoor temperature).
4. **RL Node**: Configures and starts the world-based agent — pre-trained offline and immediately ready for use.
5. **Agent Node**: Generates monthly reports, suggests adjustments to rule chains, and briefly asks for manual approval.
6. **Action Nodes**: Start/pause apps, send emails, create tickets in case of limit violations.

## **Agent Nodes – a look into the future**

In future versions, Eliona will **Agent Nodes** offer, which:

* Can be fed with domain-specific expert knowledge.
* Make decisions autonomously and derive measures.
* Independently execute actions such as forecast updates, RL control, or escalation management.
* Be integrated directly into rule chains to enable fully automated, learning building processes.

## **Benefits of AI orchestration with rule chains**

* **Centralization**: One platform for all AI modules and automation logic.
* **Flexibility**: Easy adjustment of workflows via drag and drop.
* **Transparency**: Every action is visually documented and auditable.
* **Scalability**: Usable for individual systems all the way up to thousands of assets.
* **Future-proofing**: Expandable with new AI modules such as anomaly detection or computer vision.

## **Conclusion**

With **AI orchestration in Eliona** rule chains become the centerpiece of autonomous building operations. They connect RL, forecasting, LLMs, and classic automation logic into a seamless, adaptive system — one that not only reacts, but acts proactively.\
This creates a platform that already makes operations more efficient today while also being ready for the next generation of AI-supported smart buildings.