Sensors Shape The Future Of Office BMS

Sensors Insights by Itamar Roth

Sensor technology is not new to smart buildings. Millions of office buildings around the world today are equipped with sensor-based systems designed to conserve energy, performing simple tasks such as automatically turning the lights on and off when someone enters or leaves a room. But this is just the beginning of the smart building revolution.

A truly smart building will know how the office space is being used at every single moment: how many people are in each room, how long the line is in the cafeteria, where there is a free desk, and many other aspects of the building usage. This awareness will be translated into a more cost-effective and productive working environment for the building inhabitants. In order to achieve this goal, the next generation of sensors will need to be much smarter and able to source and analyze richer levels of data, enabling the execution of more sophisticated tasks that go far beyond energy consumption management.

 

Deep Learning and Edge Analytics

Smart sensor derived data is the driving force behind widespread smart building adoption. In addition to detecting the number of occupants in a space, smart sensors should provide unprecedented detection of occupants’ locations and movements, as well as precise reading of ambient lighting and motion sensing. One approach for collecting this rich data set is to embed deep learning neural networks in IoT devices. Deep learning is an advanced approach to machine learning, where algorithms define an end-to-end computation — from the raw sensor data all the way to the final output. In this model, the algorithm must figure out for itself what the correct features are and how to compute them. This results in a much deeper level of computation that is more effective than any rule or formula used by traditional machine learning. This computation is typically performed using a neural network, a complex computational circuit with millions of parameters that the algorithm will tune until it zeros-in on the right function. Applying a deep learning neural network is advantageous for real-time systems like smart sensors because it enables significantly enhanced reliability, scalability and flexibility.

Edge computing affords the ability to process the sensor analytics inside the sensor unit itself. With this approach, the data that is sent over the network can be merely the final summary of the analysis, which is thinner in volume, and allows shorter response time. Embedded-analytics processed at the edge allow sensing solutions to extract the most important information about how and where occupants are using a building, providing real-time intelligence and greater control agility while at the same time off-loading the heavy communications traffic and saving the costs of additional processors at the cloud. This leads to dramatically reduced operational expenses and significantly enhanced workplace intelligence.

The most important merit of this approach is that it ensures the privacy and security of building occupants.

There are a number of use cases for advanced human activity sensor solutions in building management systems, including space management, booking meetings rooms, hot desking, and of course, energy efficiency.

 

Space Management

For organizations to accurately plan and manage their office spaces, smart sensors must monitor and continuously collect and analyze data about meeting rooms, open spaces and desks. By understanding the paths, durations and locations of occupants, companies can optimize the placement of appliances or devices (e.g. printers, coffee machines) in and around the environment, creating a smooth and efficient work place for employees.

Historical space utilization information is also valuable for flexible workplaces to determine if an increase or reduction in meeting spaces or desks is needed to accommodate workers. Space utilization data also provides insights for organizations to optimize required maintenance and cleaning operations.

 

Meeting Room Booking

Available meeting rooms in office buildings are typically a rare and expensive resource and require coordination to optimize their usage. Current management of meeting rooms booking is characteristically conducted manually, again without reliable real-time feedback.

Smart sensing systems allow for effective usage management by detecting presence in a meeting room, which is useful for last-minute bookings and ad hoc meetings. It allows flexible allocation based on the number of participants, assessing aggregated data of usage frequency and occupants number during meetings to provide a true understanding of how meeting rooms are used through extensive reporting. Smart sensors can also detect unused but reserved rooms and release the resource allowing other workers access if needed.

 

Hot Desking

Hot desking is the office building practice of allocating desks to workers when they are needed or on a rotating system, rather than giving each worker his/her own desk. The main motivation of this flexible approach is to reduce property costs by maximizing the usage of all available space specifically when and where there is demand.

Hot desking is typically performed using manual registration systems, which don’t include reliable real-time data, and some solutions use expensive PIR sensors at each desk to provide real-time feedback. A more accurate and cost-effective option is to implement a smart sensing solution that monitors multiple desks and provide desk-level occupancy notifications to the hot-desking application. 

 

Energy Savings

Driven by the increased need for cost savings and firm regulations, smart sensing solutions provide reliable data about occupants’ presence, count and location to enable significant energy savings in lighting and HVAC systems in several ways. The first is by daylight harvesting. Smart sensors use illumination data to control lighting intensity levels in consideration of outside lighting.

By accurately tracking occupancy count and location, smart sensors can activate lighting only when needed. Furthermore, demand control ventilation ensures a given building space is properly ventilated according to the number of occupants in the environment.

 

Conclusion

Companies that deploy smart sensing technologies, like our CogniPoint smart sensing platform, are gratified by immediate and significant results, including highly accurate occupancy detection, ease of scalability and adaptability to future enhancements. Smart sensor system that apply advanced deep learning neural network technology and edge computing to the building automation ecosystem allow facility manager to capitalize on opportunities to gather abundant data and apply efficient, real-time analytics.

Organizations can save energy by counting exactly and in real-time how many people are in a room, and use that information to adjust its ventilation. Smart sensors can see which meeting rooms are free, or where there is an unoccupied work station and by collecting statistics on the usage of the office space, organizations can use space to better suit the needs of workers. The smart building revolution is upon us and the benefits of smart sensor systems are seemingly endless.

 

About the author

Itamar Roth is the Chief Business Officer at PointGrab. He brings over 15 years of start-up experience in business, marketing, and product development with an in-depth focus on embedded systems and imaging solutions. Prior to PointGrab, Itamar led marketing and product management for the enterprise division at Anobit (acquired by Apple) and managed the professional services both at TransChip (acquired by Samsung) and at the Samsung Israel R&D Center.