Bharathan Balaji

Occupancy-driven energy management for smart building automation

Buildings are among the largest consumers of electricity in the US. A significant portion of this energy use in buildings can be attributed to HVAC systems used to maintain comfort for occupants. In most cases these building HVAC systems run on fixed schedules and do not employ any fine grained control based on detailed occupancy information. In this paper we present the design and implementation of a presence sensor platform that can be used for accurate occupancy detection at the level of individual offices. Our presence sensor is low-cost, wireless, and incrementally deployable within existing buildings. Using a pilot deployment of our system across ten offices over a two week period we identify significant opportunities for energy savings due to periods of vacancy. Our energy measurements show that our presence node has an estimated battery lifetime of over five years, while detecting occupancy accurately. Furthermore, using a building simulation framework and the occupancy information from our testbed, we show potential energy savings from 10% to 15% using our system.

Sentinel: occupancy based HVAC actuation using existing WiFi infrastructure within commercial buildings

Commercial buildings contribute to 19% of the primary energy consumption in the US, with HVAC systems accounting for 39.6% of this usage. To reduce HVAC energy use, prior studies have proposed using wireless occupancy sensors or even cameras for occupancy based actuation showing energy savings of up to 42%. However, most of these solutions require these sensors and the associated network to be designed, deployed, tested and maintained within existing buildings which is significantly costly. We present Sentinel, a system that leverages existing WiFi infrastructure in commercial buildings along with smartphones with WiFi connectivity carried by building occupants to provide fine-grained occupancy based HVAC actuation. We have implemented Sentinel on top of RESTful web services, and demonstrate that it is scalable and compatible with legacy building management. We show that Sentinel accurately determines the occupancy in office spaces 86% of the time, with 6.2% false negative errors. We high-light the reasons for the inaccuracies, mostly attributed to aggressive power management by smartphones. Finally, we actuate 23% of the HVAC zones within a commercial building using Sentinel for one day and measure HVAC electrical energy savings of 17.8%.

Managing plug-loads for demand response within buildings

Detailed and accurate energy accounting is an important first step in improving energy efficiency within buildings. Based on this information, building managers can perform active energy management, especially during demand response situations that require load shedding over short time scales. While individual plug-loads are an important target for demand response, they pose significant challenges due to their distributed nature and the significant diversity of devices that are deployed. This paper presents the design and implementation of our energy accounting and management system which is specifically geared towards managing plug-loads within enterprise buildings. Our system provides fine-grained visibility and control of plug-loads to building managers, allowing them to deal with demand response situations through user-specified actuation policies. At its core, our system consists of our wireless smart energy meter with actuation capabilities, ZigBee-based wireless network infrastructure, and our Demand Response Server, an analysis engine that provides interfaces for initiating load-shedding policies. Our micro-benchmarks show the different methods that building managers can utilize to efficiently manage devices during demand response events.

ZonePAC: Zonal Power Estimation and Control via HVAC Metering and Occupant Feedback

Heating Ventillation and Air Conditioning (HVAC) systems account for nearly 40% of primary energy consumption by commercial buildings. Yet, these systems by and large operate in an open-loop with the building occupants. While the monitoring and feedback of comfort conditions is by (much smaller) zones, the HVAC control systems operate on energy metering and monitoring at the scale of entire buildings. ZonePAC attempts to bridge this gap between metering, monitoring and control by providing an embedded sensing and information management architecture that provides for effective participation by the building occupants in zonal HVAC settings that directly affect the building scale HVAC control system. Our results from a deployment of 65 users spread across 51 zones in a 145,000 square feet commercial building demonstrate the viability and effectiveness of ZonePAC.

Brick: Towards a Unified Metadata Schema For Buildings

Commercial buildings have long since been a primary target for applications from a number of areas: from cyber-physical systems to building energy use to improved human interactions in built environments. While technological advances have been made in these areas, such solutions rarely experience widespread adoption due to the lack of a common descriptive schema which would reduce the now-prohibitive cost of porting these applications and systems to different buildings. Recent attempts have sought to address this issue through data standards and metadata schemes, but fail to capture the set of relationships and entities required by real applications. Building upon these works, this paper describes Brick, a uniform schema for representing metadata in buildings. Our schema defines a concrete ontology for sensors, subsystems and relationships among them, which enables portable applications. We demonstrate the completeness and effectiveness of Brick by using it to represent the entire vendor-specific sensor metadata of six diverse buildings across different campuses, comprising 17,700 data points, and running eight complex unmodified applications on these buildings.

Data driven investigation of faults in HVAC systems with model, cluster and compare (MCC)

The complexity of modern HVAC systems leads to device mis-configuration in about 40% of buildings, wasting upto 40% of the energy consumed. Fault detection methods generate excessive alarms leading to operator alert fatigue, faults left unfixed and energy wastage. Sophisticated fault detection techniques developed in the literature are seldom used in practice. We investigate this gap by applying various fault detection techniques on real data from a 145,000 sqft, five floor building. We first find that none of these algorithms are designed to capture control loop configuration faults. We develop a novel algorithm, Model, Cluster and Compare (MCC) that is able to detect anomalies by automatically modeling and clustering similar entities in an HVAC system, in an unsupervised manner, and comparing them. We implemented MCC to detect faults in Variable Air Volume boxes in our building, and demonstrate that it successfully detects non-obvious configuration faults. We propose a two stage approach, where we design intelligent rules (iRules) based on anomaly exemplars from a mix of data driven algorithms. iRules are successful in capturing a large fraction of faults in our building, with only one false alarm and 78 anomalies detected out of 237 zones. Thus, comparative data mining is useful in filtering the large amount of data generated in modern buildings, but that human in the loop systems are better still.

BuildingRules: a trigger-action based system to manage complex commercial buildings

Modern Building Management Systems (BMSs) provide limited amount of control to its occupants, and typically allow only the facility manager to set the building policies. BuildingRules let occupants to customise their office spaces using trigger-action programming. In order to accomplish this task, BuildingRules automatically detects conflicts among the policies expressed by the users using a SMT based logic. We tested our system with 23 users across 17 days in a virtual office building, and evaluate the effectiveness and scalability of the system.

A wi-fi based occupancy sensing approach to smart energy in commercial office buildings

Buildings account for a considerable part of energy consumption. Prior research has shown that much energy could be saved by using occupancy based building automation techniques. One of the remaining challenges is how to collect real-time occupancy information that is practically accurate yet without incurring high deployment costs. We will demonstrate a prototype system that is being experimented in a typical IT office building. Our system derives coarse-grained occupancy information by sniffing wi-fi signals and fine-grained information by wi-fi based indoor positioning. The synthesized information provides sufficient accuracy for zone-based HVAC and lighting control. Due to wide-spread usage of wireless APs and mobile devices in IT buildings today, the deployment cost of our system is low.

A Novel Power Saving Strategy for Greening IEEE 802.11 Based Wireless Networks

We propose a novel power saving strategy called Sleep during Neighbor-Addressed Frame (SNAF) for improving energy efficiency of IEEE 802.11 based wireless networks. IEEE 802.11 (Wi-Fi) radios that employ SNAF mode can turn OFF their wireless transceivers (i.e., put radios in sleep mode) within specific periods of neighbor-addressed frames while they are being received. The sleep duration of transceivers is easy to determine with no loss of packets critical control information. The proposed SNAF mode operation does not have any negative effect on network throughput and even complements Power Saving Mode (PSM) available in 802.11 standard. We further propose GreenFrame format for next generation wireless networks. In experiments conducted in wireless LAN scenarios, we observed savings as much as 57.8% when we implement SNAF mode in 802.11 standard and up to 49.5% when we implement SNAF mode in 802.11 PSM.

Models, abstractions, and architectures: the missing links in cyber-physical systems

Bridging disparate realms of physical and cyber system components requires models and methods that enable rapid evaluation of design alternatives in cyber-physical systems (CPS). The diverse intellectual traditions of physical and mathematical sciences makes this task exceptionally hard. This paper seeks to explore potential solutions by examining specific examples of CPS applications in automobiles and smart buildings. Both smart buildings and automobiles are complex systems with embedded knowledge across several domains. We present our experiences with development of CPS applications to illustrate the challenges that arise when expertise across domains is integrated into the system, and show that creation of models, abstractions, and architectures that address these challenges are key to next generation CPS applications.