Jonathan Fürst

Leveraging Physical Locality to Integrate Smart Appliances in Non-Residential Buildings with Ultrasound and Bluetooth Low Energy

Smart appliances and sensors have become widely available. We are deploying them in our homes to manage the level of comfort, energy consumption or security. While such smart appliances are becoming an integral part of modern home automation systems, their integration into non-residential buildings is problematic. Indeed, smart appliance vendors rely on the assumption that the Local Area Network (LAN) guarantees locality and a single unit of use/administration. This assumption is not met in non-residential buildings, where the LAN infrastructure might cover one or several buildings, and where several organizations or functional units are co-located. Worse, directly coupling smart appliances to the Internet opens up a range of security issues as device owners have very little control over the way their smart appliances interact with external services. In order to address these problems, we propose a solution that couples the use and management of smart appliances with physical locality. Put differently, we propose that smart appliances can be accessed via smartphones, but only from the room they are located in. Our solution combines opportunistic connectivity through local Bluetooth Low Energy (BLE) with an ultrasound-based method for room level isolation. We describe and evaluate a prototype system, deployed in 25 offices and 2 common spaces of an office building. This work opens up intriguing avenues for new research focused on the representation and utilization of physical locality for decentralized building management.

BUSICO 3D: building simulation and control in unity 3D

In this demonstration, we present a novel system of building control and simulation focused on the integration of the physical and virtual worlds. Actuations and schedules can be manifested either in a physical space or in a virtualization of that space, allowing for more natural interactions with simulations and easier transferring of schedules and configurations from the simulated virtual environment to a real-world deployment. We provide an implementation using a widely used game engine (Unity 3D) and sMAP (Simple Measurement and Actuation Profile), a developed time series database and metadata store.

Demo Abstract: Human-in-the-loop BMS Point Matching and Metadata Labeling with Babel

The inconsistent metadata in Building Management Systems (BMS) hinders the deployment of cyber-physical applications in non-residential buildings. In this demonstration we present Babel, a continuous, human-in-the-loop and crowdsourced approach to the creation and maintenance of BMS metadata. Occupants provide physical and digital input in form of actuations (e.g., the switching of a light) and readings (e.g., the reading of the room temperature of a thermostat) to Babel. Babel then matches this input to digital points in the BMS based on value equality. We have implemented a prototype of our system in a non-residential building over the BACnet protocol. While our approach can not solve all metadata problems, this demonstration illustrates that it is able to match many relevant points in a fast and precise manner.

SnapLink: Fast and Accurate Vision-Based Appliance Control in Large Commercial Buildings

As the number and heterogeneity of appliances in smart buildings increases, identifying and controlling them becomes challenging. Existing methods face various challenges when deployed in large commercial buildings. For example, voice command assistants require users to memorize many control commands. Attaching Bluetooth dongles or QR codes to appliances introduces considerable deployment overhead. In comparison, identifying an appliance by simply pointing a smartphone camera at it and controlling the appliance using a graphical overlay interface is more intuitive. We introduce SnapLink, a responsive and accurate vision-based system for mobile appliance identification and interaction using image localization. Compared to the image retrieval approaches used in previous vision-based appliance control systems, SnapLink exploits 3D models to improve identification accuracy and reduce deployment overhead via quick video captures and a simplified labeling process. We also introduce a feature sub-sampling mechanism to achieve low latency at the scale of a commercial building. To evaluate SnapLink, we collected training videos from 39 rooms to represent the scale of a modern commercial building. It achieves a 94% successful appliance identification rate among 1526 test images of 179 appliances within 120 ms average server processing time. Furthermore, we show that SnapLink is robust to viewing angle and distance differences, illumination changes, as well as daily changes in the environment. We believe the SnapLink use case is not limited to appliance control: it has the potential to enable various new smart building applications.

Crowd-sourced BMS point matching and metadata maintenance with Babel

Cyber-physical applications, deployed on top of Building Management Systems (BMS), promise energy saving and comfort improvement in non-residential buildings. Such applications are so far mainly deployed as research prototypes. The main roadblock to widespread adoption is the low quality of BMS metadata. There is indeed a mismatch between (i) the anecdotal nature of metadata for legacy BMS - they are usually initialized when the BMS is commissioned and later neglected-, and (ii) the imperious need for consistent and up-to-date metadata for supporting building analytics or personalized control systems. Such applications access sensors and actuators through BMS metadata in form of point labels. The naming of labels is however often inconsistent and incomplete. To tackle this problem, we introduce Babel, a crowd-sourced approach to the creation and maintenance of BMS metadata. In our system, occupants provide physical and digital input in form of actuations (e.g., the turning on/off a light) and readings (e.g., reading room temperature of a thermostat) to Babel. Babel then matches this input to digital points in the BMS based on value equality. We have implemented a prototype of our system in a non-residential building. While our approach can not solve all metadata problems, we show that it is able to match end-user relevant points in a fast and precise manner.

A Practical Model for Human-Smart Appliances Interaction: Poster Abstract

Buildings are increasingly equipped with smart appliances that allow a fine grained adaption to personal comfort requirements. Such comfort adaption should be based on a human-feedback loop and not on a centralized comfort model. We argue that this feedback-loop should be achieved through local interaction with smart appliances. Two issues stand out: (1) How to impose logical locality when interacting with a smart appliance? (2) How to mediate conflicts between several persons in a room, or between building-wide policies and user preferences? We approach both problems by defining a general model for human-smart appliance interaction. We present a prototype implementation with an off-the-shelf smart lighting and heating system in a shared office space. Our approach minimizes the need for location metadata. It relies on a human-feedback loop (both sensor based and manual) to identify the optimal setpoints for lights and heating. These setpoints are determined by considering individual comfort preferences, current user location and a global goal of minimizing energy consumption.

COSMGrid: Configurable, off-the-shelf micro grid

Access to modern energy services should be universally available by 2030. This is a goal of the United Nations. A promising approach to deliver on this commitment is based on microgrids that coordinate power generation, storage and usage in a local community. Microgrids constitute an attractive option in the presence of abundant renewable energy sources, and in the absence of robust transnational power grid infrastructure. An important problem is then to design cheap, resilient and configurable microgrids that can be assembled from off-the-shelf components and managed by non specialists. In this paper, we introduce COSMGrid, a microgrid platform based on commodity hardware and open source, open protocol software. The design of COSMGrid relies on a network of microcontrollers that monitor and control stand-alone power generation and storage nodes. As a result, COSMGrid can readily integrate existing stand-alone photovoltaic installations. COSMGrid can be configured based on the characteristics of the power electronics hardware that is available, or based on the power sharing policies agreed upon by a community of end-users. It is an important step towards a popular, open microgrid solution that can be appropriated by local communities in developing regions.