Projects
Towards the realization of smart building applications, buildings are increasingly instrumented with diverse sensors and actuators. These sensors generate large volumes of data which can be analyzed for optimizing building operations. Many building energy management tasks such as energy forecasting, disaggregation, among others require complex analytics leveraging collected sensor data. While several standalone and cloud-based systems for archiving, sharing and visualizing sensor data have emerged, their support for analyzing sensor data streams is primitive and limited to rule-based actions based on thresholds and simple aggregation functions. We develop OpenBAN, an open source sensor data analytics middleware for buildings, to make analytics an integral component of modern smart building applications. OpenBAN provides a framework of extensible sensor data processing elements for identifying various building context, which different applications can leverage. We validate the capabilities of OpenBAN by developing three representative real-world applications which are deployed in our test-bed buildings: (i) household energy disaggregation, (ii) detection of sprinkler usage from water meter data, and (iii) electricity demand forecasting. We also provide a preliminary system performance analysis of OpenBAN when deployed in the cloud and locally within a building.
Team members: Pandarasamy Arjunan, Kevin Ting (UCLA)
Advisors: Dr. Amarjeet Singh, Dr. Pushpendra Singh and Prof. Mani B Srivastava (UCLA)
Source: github
The archaic centralized software systems, currently used to manage buildings, make it hard to incorporate advances in sensing technology and user-level applications, and present hurdles for experimental validation of open research in build- ing information technology. Motivated by this, we — a transnational collaboration of researchers engaged in development and deployment of technologies for sustainable buildings — have developed SensorAct, an open-source federated middleware incorporating features targeting three specific requirements: (i) Accommodating a richer ecosystem of sensors, actuators, and higher level third-party applications (ii) Participatory engagement of stakeholders other than the facilities department, such as occupants, in setting policies for management of sensor data and control of electrical systems, without compromising on the overall privacy and safety, and (iii) Flexible interfacing and information exchange with systems external to a building, such as communication networks, transportation system, electrical grid, and other buildings, for better management, by exploiting the teleconnections that exist across them. SensorAct is designed to scale from small homes to network of buildings, making it suitable not only for production use but to also seed a global-scale network of building testbeds with appropriately constrained and policed access.
Team members: Pandarasamy Arjunan, Nipun Batra and Haksoo Choi (UCLA)
Advisors: Dr. Amarjeet Singh, Dr. Pushpendra Singh and Prof. Mani B Srivastava (UCLA)
Source: github
MELOS (Mobile Extension for LOw-energy Sensing) is a low-cost generic sensing attachment for mobile phones. Since MELOS interfaces with mobile phone through audio jack, it can be connected to almost all the mobile phones, including low-end non-programmable phones. MELOS has inbuilt micro SD card for local storage and Bluetooth for short range communication. We can connect multiple sensors and appliances through actuators to MELOS and they can be controlled remotely through cellular network using DTMF tones by making phone call. MELOS along with low-end mobile phones can be used as a low-cost sensing platform for various applications like energy monitoring, environmental sensing.
Team members: Abhishek Bhardwarj and Pandarasamy Arjunan
Advisors: Dr. Amarjeet Singh, Dr. Vinayak Naik and Dr. Pushpendra Singh