How Nexus BMS Uses Time Series and AI to Power Smarter Buildings
By
Charles Mahler /
Developer
Sep 25, 2025
Navigate to:
Monitoring equipment isn’t enough for today’s smart buildings; true value comes from being able to predict issues, optimize performance, and take action automatically. Traditional building management systems often fall short, limited to dashboards and alarms that only notify you of an issue after the fact. With the rise of open source hardware, modern databases, and AI-driven diagnostics, facilities can now move from reactive to proactive management.
In this blog, we’ll recap how Nexus BMS leverages InfluxDB, edge controllers, and AI models to not only monitor but also directly control building equipment across diverse environments—from clean rooms to healthcare facilities. For a full walkthrough of the system and its capabilities, be sure to watch the complete webinar.
What is Nexus?
Nexus BMS is a building management system (BMS) designed to replace or complement existing legacy systems. Traditional BMS solutions often stop at monitoring, simply collecting sensor data and displaying it on dashboards. Nexus goes a step further by combining real-time monitoring, direct equipment control, and predictive AI diagnostics into one unified platform.
Nexus is designed to solve real-world problems: broken controllers, rising licensing fees, and facility managers left without reliable tools to operate critical infrastructure. Instead of just alerting when something goes wrong, Nexus continuously processes thousands of sensor readings, applies custom control logic, and can adjust equipment automatically, whether that means fine-tuning a fan coil, modulating a pump, or holding tight tolerances in clean rooms and healthcare environments.
The Nexus platform allows for active control of equipment by providing these features:
- Sensor Inputs - Environmental and mechanical data (temperature, humidity, vibration, current draw, etc.) flow from sensors into Raspberry Pi edge controllers.
- Logic Execution - Custom control logic, written and stored on the server, determines the correct equipment responses based on live data and user-set thresholds.
- Command Generation - Nexus generates control commands—such as adjusting fan coil outputs, changing supply air temperature setpoints, or modulating pumps.
- Edge Execution - These commands are sent back to Node-RED workflows or directly executed on the Pi controllers, which then actuate relays, valves, or motors.
- User Oversight - Every change is authenticated, logged, and emailed to facility staff for full accountability.
This architecture enables Nexus to detect issues early and take immediate corrective action, ensuring comfort, safety, and efficiency in facilities where environmental control is critical.
Why is time series data needed to power smart buildings?
Smart buildings operate on data, specifically time series data. This is information that is collected, ordered, and stored over time, such as temperature readings, the current draw of a chiller motor, or humidity levels in a clean room. In Nexus BMS, every piece of equipment streams metrics continuously, creating a living dataset that reflects the real-time pulse of a facility.
How Nexus BMS Uses Time Series Data
Time series data is the backbone of Nexus, enabling:
- Real-time responsiveness – With new metrics arriving every 15 seconds, the system can instantly detect changes and push control commands to equipment before small fluctuations become big problems.
- AI model training – Predictive diagnostics depend on historical patterns. Feeding consistent time series data into Nexus’s seven AI models enables accurate anomaly detection and proactive maintenance.
- Fine-grained analysis – Facility managers can slice and query data by device, location, or condition to uncover performance inefficiencies that would otherwise stay hidden.
- Trend recognition – Subtle shifts in amp draws, temperature curves, or vibration levels reveal early signs of equipment wear long before alarms are triggered.
Using a time series database like InfluxDB allows Nexus to store high-precision data for longer, saving money and providing users with a better experience due to improved performance compared to general-purpose databases.
Nexus tech stack
Frontend
For the frontend architecture, NextJS provides the framework with ShadCN used for styling. This frontend enables authenticated users to view real-time dashboards, run AI-powered diagnostics with a single click, and manually adjust equipment settings.
Backend
The Nexus backend is a collection of databases that uses NodeJS for programming logic. InfluxDB is at the core of all sensor data utilized in dashboards and model training. Postgres is used for storing configuration as well as AI training records. Redis is also used for caching stateful equipment control data.
Edge Hardware
A number of different hardware devices can deploy Nexus in facilities. Raspberry Pi 5s with 1TB SSDs are used at each site, running Node-RED flows and custom control logic. SQLite databases are installed locally to allow offline operation if network connectivity is lost.
Sequent microsystems boards interface directly with facility equipment, with support for analog and digital signals. Examples of devices include temperature sensors, vibration monitoring systems, and current transducers. Training models utilize Hailo AI accelerator chips.
Next steps
The Nexus BMS story demonstrates what’s possible when real-world expertise meets modern data infrastructure and AI. By combining time series data, open source hardware, and predictive modeling, Nexus transforms building automation from simple monitoring into a proactive, intelligent system that enhances reliability, efficiency, and safety.
If you’re interested in the future of smart building management, be sure to watch the full webinar.
