Smart Buildings

Take Energy and Maintenance Efficiency to the Next Level

Among the many benefits of using FogHorn’s Edge AI platform for smart buildings are lower energy consumption, predictive maintenance, better security, increased occupant comfort and safety, and better utilization of building assets and services. Rather than sending massive amounts of building data to the cloud for analysis, smart buildings can use FogHorn’s edge intelligence for more responsive automation while reducing bandwidth costs and latency.

Use Cases

Operational
Intelligence

Optimize systems for maximum KPI performance, quickly adjust to changing conditions.

Prescriptive
Maintenance

Reduce repair costs, minimize downtime, maximize output, and improve remediation efficiency.

Condition-based
Monitoring

Lower maintenance costs, improve asset performance and longevity, and maximize yield.

Energy Usage
Optimization

Maximize high-value asset output, balance reliability, performance, and cost.

Examples

Intelligent Building Energy Management 

From commercial buildings to school and university campuses, industry estimates have shown that 20-30% of energy spending could be saved through more efficient use of heating, cooling and lighting systems. The most effective way to reduce energy consumption is to engage in a portfolio-wide, systematic approach to improving energy efficiency. A new layer of intelligence is required that can tune existing systems to be used when and where their needed based on real-team conditions.

A building edge AI platform collects data from temperature sensors, room schedules, occupancy sensors, weather forecasts, and time-of-day energy rates. Machine learning models and AI are applied to this data and automatically determines the optimal heating or cooling profile for each room, building, and campus across the entire portfolio to realize the most efficient energy use while balancing occupant comfort. The AI platform is continuously executing against this real-time data to react to any changing conditions and make optimizations immediately.

The platform ingests other sensor data, including vibration sensors, flow meters, temperature probes, and more, to ensure HVAC equipment’s optimal performance and energy use. Predictive models are also employed to gauge the proper maintenance and replacement of this critical infrastructure.

As an edge-native AI platform, data is being ingested, enriched and analyzed in real-time, on-premise at each building. This approach provides robust security as sensitive data stays on-site and saves tremendous amounts of money in data transmission, bandwidth, storage and cloud platform costs. Only the insights discovered at each edge location are published to a federated view accessible in the cloud.

Avoid the pain and expense of a rip-and-replace exercise to upgrade building management systems and bring in a new Edge AI layer that orchestrates your existing BMS investments.

Optimizing Elevator Performance with On-board Edge Computing

There is tremendous value in analyzing the 1 GB+ of sensor data each elevator can produce daily to anticipate maintenance needs, avoid downtime, minimize expensive repair and replacement costs, and ensure a high level of customer satisfaction. Cloud-based solutions do not scale to address these challenges. The simple cost to move GBs of data a day over a 4G cellular connection for thousands of elevators would be untenable. Not to mention the costs of cloud storage for all of this data.

The solution requires adding FogHorn Lightening Edge AI to each elevator’s core motion sensor kit, a small ARM-based gateway with 200-300 MB of available memory that monitors temperature, humidity, 3-axis accelerometers, braking and other data. With edge insights, they can move to smart prescriptive maintenance, reducing costly repairs and servicing and avoid costly investments in bandwidth and cloud computing charges.