> For the complete documentation index, see [llms.txt](https://docs.buildings.ability.abb/collection/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.buildings.ability.abb/collection/success-stories/energy-optimization-using-artificial-intelligence.md).

# Energy Optimization Using Artificial Intelligence

AI-based energy optimization across an international finance portfolio.

**Industry:** Banking and Finance\
**Organization:** International finance institute\
**Scope:** 14 buildings, with a planned rollout to more than 100\
**Year:** 2024

## At a Glance

| Measure             | Result                                          |
| ------------------- | ----------------------------------------------- |
| Energy savings      | 27% in the first three months                   |
| Proof of concept    | Up to 25% reduction in one building             |
| Buildings optimized | 14, with expansion planned                      |
| Data foundation     | Semantic harmonization across heterogeneous BMS |

## Overview

An international finance institute wanted to reduce operating costs and improve sustainability ratings across an existing building portfolio. BuildingPro Suites connects heterogeneous building-management systems, establishes transparent consumption baselines, and provides the structured data required by cloud-based AI optimization.

## From Monitoring to Optimization

Monitoring first made consumption patterns and improvement potential visible. A digital twin was then created for each building to model energy flows using historical consumption, current and historical weather, and occupancy data.

The AI identifies inefficient operation and calculates optimized target values, which are returned to the building-management systems. This turns portfolio analytics into active operational improvement rather than reporting alone.

## Semantic Data Foundation

The existing BMS landscape contained different systems, versions, and data structures. BuildingPro Suites organizes, tags, and translates incoming data into an ontological semantic model. This consistent foundation allows optimization methods to be applied across buildings without treating every datapoint as an isolated custom integration.

## Scaling and Resilience

The project showed that data quality and relevance matter more than collecting the maximum possible number of points. Depending on the building, AI models may use fewer than 1,000 or as many as 15,000 datapoints. Containerized services, security checks, and store-and-forward communication support a secure rollout toward more than 100 buildings while preserving an audit trail during interruptions.

The result was 27% total energy savings during the first three months of operation, following a proof of concept that achieved up to 25% savings in one building.

[-> \[External Link\] Read the complete success story](https://stage.advisor.buildings.ability.abb/success-stories/finance-energy-optimization)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.buildings.ability.abb/collection/success-stories/energy-optimization-using-artificial-intelligence.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.