Indoor Path Planning and Decentralized Access Control in Commercial BuildingsC-IoT2 University of Alberta | Presentation | 2019-11-01 | |
Decentralized Access Control for Smart Buildings Using Metadata and Smart ContractsManaging the privileges of occupants and visitors of large commercial buildings to access different building areas, control systems and equipment therein is a challenging task. The best practice today involves giving long-term building occupants, for example employees working in the building, access privileges to their organization areas and requiring visitors to be escorted by them. This approach is conservative and inflexible. Ideally, an automated solution is needed to manage access delegations; how- ever, traditional role-based access control models are unwieldy in that they require the specification of all roles and their relative authority, which is a challenge in large buildings home of multiple organizations and numerous visitors. In this paper, we present a methodology based on blockchain smart contracts to describe, grant, and revoke fine-grained permissions for building users in a decentralized fashion. This method supports access control using resource description framework (RDF) graphs and implements two APIs for client applications. Leveraging the metadata of a real building, we have applied the proposed method to manage privileges in some realistic use-cases and shown that it can greatly reduce the administration overhead while providing fine-grained access control. University of Alberta | Publication | 2019-05-01 | |
Evaluating and Improving the Energy Performance of School Buildings with a Proposed Real-Time Monitoring System University of Alberta | Publication | 2018-11-01 | |
Bayesian Learning-Based Harmonic State Estimation in Distribution Systems With Smart Meter and DPMU DataThis paper studies the problem of locating harmonic sources and estimating the distribution of harmonic voltages in unbalanced three-phase power distribution systems. We develop an approach for harmonic state estimation utilizing two types of measurements from smart meters and distribution-level phasor measurement units (DPMUs). It involves regression analysis for power flow calculation, prediction of demands using recurrent neural networks, and sparse Bayesian learning for state estimation. The proposed approach requires fewer DPMUs than nodes, making it more applicable to existing distribution grids. We show the effectiveness of the proposed estimator through extensive numerical simulations on an IEEE test feeder. We also investigate how the increased penetration of distributed energy resources could affect the performance of our state estimator. University of Alberta | Publication | 2020-01-01 | |
Guest Editorial Theory and Application of PMUs in Power Distribution Systems University of Alberta | Publication | 2020-01-01 | Hamed Mohsenian-Rad, Mario Paolone, Vassilis Kekatos, Omid Ardakanian, Yan Xu, Di Shi, Reza Arghandeh |
Practical Considerations in the Design of Distribution State Estimation Techniques University of Alberta | Publication | 2019-10-01 | |
On Identification of Distribution GridsLarge-scale integration of distributed energy resources into distribution feeders necessitates careful control of their operation through power flow analysis. While the knowledge of the distribution system model is crucial for this analysis, it is often unavailable or outdated. The recent introduction of synchrophasor technology in low-voltage distribution grids has created ample opportunity to learn this model from high-precision, time-synchronized measurements of voltage and current phasors at various locations. This paper focuses on joint estimation of admittance parameters and topology of a poly-phase distribution network from the available telemetry data via the lasso, a method for regression shrinkage and selection. We propose tractable convex programs capable of tackling the low rank structure of the distribution system and develop an online algorithm for early detection and localization of critical events that induce a change in the admittance matrix. The efficacy of these techniques to identify a large part of the distribution network is corroborated through power flow studies on four three-phase radial distribution systems serving real and synthetic household demands. University of Alberta | Publication | 2019-09-01 | Omid Ardakanian, Vincent Wong, Roel Dobbe, Alexandra Von Meier, Steven Low, Claire Tomlin, Ye Yuan |
EnergyBoost: Learning-based Control of Home BatteriesBest Paper Award Finalist The falling costs of battery storage and photovoltaic systems have substantially increased the number of "solar-plus-battery" installations in homes and buildings. The solar-plus-battery system enables homeowners to protect their homes during a power outage and save on their electricity bills by stacking multiple value streams that battery storage can provide. In this paper, we present EnergyBoost, a system that proactively controls battery charge and discharge operations, and investigate whether it makes sense economically to install a battery controlled by this system in different jurisdictions with distinct tariff structures. EnergyBoost solves an optimal control problem over a finite time horizon relying on physical models of a solar inverter and a lithium-ion battery, and supervised learning models for predicting the next day available solar energy and household demand. We propose two learning-based control algorithms for EnergyBoost, namely model predictive control and advantage actor-critic. We implement these algorithms on a Raspberry Pi and compare their performance with a rule-based controller under various pricing schemes using real traces of solar irradiance and power consumption of 70 homes located in the same jurisdiction. Our results indicate that EnergyBoost'S control policy outperforms the baseline policies in terms of reducing the average monthly electricity bill, yielding a bill that is, on average, only 7.6% worse than the best bill that can be theoretically achieved. University of Alberta | Publication | 2019-06-01 | |
A domain adaptation technique for fine-grained occupancy estimation in commercial buildingsFine-grained occupancy information is essential to improve human experience and operational efficiency of buildings, yet it is quite challenging to obtain this information due to the lack of special-purpose sensors for occupancy monitoring, and insufficient training data for developing accurate data-driven models. This paper addresses this challenge by (a) utilizing recurrent neural network models to uncover latent occupancy patterns in individual rooms from trend data available through the building management system, and (b) applying a domain adaptation technique to transfer existing occupancy models trained in a controlled environment (i.e., the source domain) to another environment (i.e., the target domain) where labelled data is sparse or non-existent. We adjust the model parameters based on the apparent differences between the two environments and apply the adapted model to estimate the number of occupants in the target domain. Our results from two test commercial buildings in two continents indicate that the adapted model yields only slightly lower accuracy than a model that is originally built on the target domain given a large amount of labelled data. Furthermore, we study how much labelled data is required from the target domain for the semi-supervised domain adaptation technique to achieve promising results.P-Apps27 University of Alberta | Publication | 2019-04-01 | |
Sparse Bayesian Harmonic State EstimationThis paper presents a novel iterative method for harmonic state estimation based on the sparse Bayesian learning framework. The proposed method can locate harmonic sources and estimate the distribution of harmonic voltages using fewer harmonic meters than buses, despite the strong correlation between the columns of the system matrix. Extensive simulations are performed on a benchmark transmission system to corroborate the efficacy of this method when measurements are noise free. Our results show that the proposed state estimator achieves an identification error of less than 1.6×10^-6 and can locate harmonic sources with an average success rate of 97.92%, outperforming state-of-the-art harmonic state estimators. University of Alberta | Publication | 2018-10-01 | |
Non-intrusive occupancy monitoring for energy conservation in commercial buildingsThe Heating Ventilation and Air Conditioning (HVAC) system of commercial buildings traditionally runs on a fixed schedule that does not take occupancy into account despite its huge variation over space and time, thereby wasting a lot of energy in conditioning empty or partially-occupied spaces. Occupancy information is essential to eliminate wasteful energy use with imperceptible impact on building operations and human comfort. This paper investigates the application of non-intrusive techniques to obtain a rough estimate of occupancy from coarse-grained measurements of sensors that are commonly available through the building management system. Various static and adaptive energy-efficient schedules are developed based on this approximate knowledge of occupancy at the level of individual zones. Our experiments in three large commercial buildings confirm that the proposed techniques can uncover the recurring occupancy pattern of the zones, and schedules that incorporate these occupancy patterns can achieve more than 38% reduction in reheat energy consumption while maintaining indoor thermal comfort. University of Alberta | Publication | 2018-11-01 | |
Data-driven occupant modeling strategies and digital tools enabled by IEA EBC annex 79The developments in sensing modalities and computing platforms enable many new sensing technologies and data sources for monitoring occupant presence and actions. The wealth of data opens new opportunities for extracting knowledge through data-driven modeling of occupant presence and actions. In particular, the many opportunities with machine learning techniques including supervised and unsupervised learning for classification, regression and clustering problems. Utilizing these opportunities creates new models and information relevant for generating new knowledge on multi-aspect environmental exposure, building interfaces, human behaviour, occupant-centric building design and operation. Subtask 2 of the new IEA EBC Annex 79 is addressing these opportunities and is inviting researchers and practitioners to participate. The developed data-driven models can, among others, be applied for example for calculating new schedules or models based on the actual conditions observed in buildings, data-driven analysis of the performance design versus the built, model predictive controls for buildings and fault detection and diagnostics. University of Alberta | Presentation | 2018-11-01 | Mikkel Baun Kjærgaard, Bing Dong, Salvatore Carlucci, Flora D. Salim, Junjing Yang, Clinton J. Andrews, Omid Ardakanian |
Real-Time Distributed Control for Smart Electric Vehicle Chargers: From a Static to a Dynamic Study University of Alberta | Publication | 2014-01-01 | |
RealTime distributed congestion control for electrical vehicle chargingThe significant load and unpredictable mobility of electric vehicles (EVs) makes them a challenge for grid distribution systems. Unlike most current approaches to control EV charging, which construct optimal charging schedules by predicting EV state of charge and future behaviour, we leverage the anticipated widespread deployment of measurement and control points to propose an alternative vision. In our approach, drawing from a comparative analysis of Internet and distribution grid congestion, control actions taken by a charger every few milliseconds in response to congestion signals allow it to rapidly reduce its charging rate to avoid grid congestion. We sketch three control schemes that embody this vision and compare their relative merits and demerits. University of Alberta | Publication | 2012-12-01 | |
A Co-simulation Platform for Evaluating Cyber Security and Control Applications in the Smart Grid University of Alberta | Publication | 2020-06-01 | |
Reputation-based Fair Power Allocation to Plug-in Electric Vehicles in the Smart Grid University of Alberta | Publication | 2020-04-01 | |
Device Mobility Detection Based on Optical Flow and Multi-Receiver Consensus University of Alberta | Publication | 2019-10-01 | |
Adaptive Control of Plug-in Electric Vehicle Charging with Reinforcement Learning University of Alberta | Publication | 2020-06-01 | |
Data-Driven Models for Building Occupancy Estimation University of Alberta | Publication | 2018-06-01 | |
Absorbing Excess PV Generation by Controlling EV Chargers University of Alberta | Presentation | 2016-09-01 | |
Non-Intrusive Techniques for Establishing Occupancy Related Energy Savings in Commercial BuildingsWinner of best paper award University of Alberta | Publication | 2016-11-01 | |
Synchrophasor Data Analytics in Distribution Grids University of Alberta | Publication | 2017-04-01 | |
Quantifying the Benefits of Extending Electric Vehicle Charging Deadlines with Solar Generation University of Alberta | Publication | 2014-11-01 | |
On the Use of Teletraffic Theory in Power Distribution Systems University of Alberta | Publication | 2012-05-01 | |
Integration of Renewable Generation and Elastic Loads into Distribution Grids University of Alberta | Publication | 2016-06-01 | |
Computing Electricity Consumption Profiles from Household Smart Meter Data University of Alberta | Publication | 2014-03-01 | Omid Ardakanian, Negar Koochakzadeh, Rayman Preet Singth, Lukas Golab, Srinivasan Keshav |
Distributed Control of Electric Vehicle ChargingWinner of best paper award University of Alberta | Publication | 2013-05-01 | |
Markovian Models for Home Electricity Consumption University of Alberta | Publication | 2011-08-01 | |
Using Decision Making to Improve Energy Efficiency of Buildings University of Alberta | Publication | 2010-05-01 | |
Mobility Aware Distributed Topology Control in Mobile Ad-Hoc Networks Using Mobility Pattern Matching University of Alberta | Publication | 2009-10-01 | MH Khaledi, Seyed Morteza Mousavi, Hamid Reza Rabiee, Ali Movaghar, MJ Khaledi, Omid Ardakanian |
On the Impact of Storage in Residential Power Distribution SystemsIt is anticipated that energy storage will be incorporated into the distribution network component of the future smart grid to allow desirable features such as distributed generation integration and reduction in the peak demand. There is, therefore, an urgent need to understand the impact of storage on distribution system planning. In this paper, we focus on the effect of storage on the loading of neighbourhood pole-top transformers. We apply a probabilistic sizing technique originally developed for sizing buffers and communication links in telecommunications networks to jointly size storage and transformers in the distribution network. This allows us to compute the potential gains from transformer upgrade deferral due to the addition of storage. We validate our results through numerical simulation using measurements of home load in a testbed of 20 homes and demonstrate that our guidelines allow local distribution companies to defer trans- former upgrades without reducing reliability. University of Alberta | Publication | 2012-12-01 | |
In (Stochastic) Search of a Fairer Alife University of Alberta | Publication | 2018-12-01 | |
Current practices and infrastructure for open data based research on occupant-centric design and operation of buildingsP-Apps27 University of Alberta | Publication | 2020-06-01 | Mikkel Kjærgaard, Omid Ardakanian, Salvatore Carlucci, Bing Dong, Steven Firth, Nan Gao, Gesche Huebner, Ardeshir Mahdavi, Mohammad Rahaman, Flora Salim, Fisayo Sangogboye, Jens Schwee, Dawid Wolosiuk, Yimin Zhu |
ODToolkit: Extensible Toolkit for Occupancy Detection in Smart BuildingsRecent years have witnessed a steady increase in the number of occupancy detection algorithms and people counting systems designed for residential and commercial buildings, yet comparing the accuracy of existing solutions has been impossible to date due to the lack of publicly available test data sets, open-source implementation of the state-of-the-art algorithms, and consensus on the evaluation metrics. This paper addresses this problem by presenting the design and implementation of an open-source toolkit for occupancy detection. ODToolkit is capable of importing and converting sensor data acquired from various buildings into a common data format, provides implementation of a broad suite of data-driven occupancy detection techniques, and calculates a set of evaluation metrics for each experiment. We present several case studies to show how this toolkit facilitates the development of new occupancy detection algorithms. In particular, we extend this toolkit by implementing novel domain-adaptive occupancy detection algorithms and compare them with the benchmark supervised learning algorithms on multiple data sets. Furthermore, we investigate what sensing modalities and precision are needed to achieve a desired level of accuracy for occupancy estimation through sensor fusion. ODToolkit code and documentation are available at https://odtoolkit.github.io/.P-Apps27 University of Alberta | Publication | 2019-06-01 | |
Event Detection and Localization in Distribution Grids with Phasor Measurement UnitsWinner of "best of the best" conference papers award University of Alberta | Publication | 2017-07-01 | Omid Ardakanian, Ye Yuan, Roel Dobbe, Alexandra Von Meier, Steven Low, Claire Tomlin |
On the Joint Control of Multiple Building Systems with Reinforcement LearningC-IoT2 University of Alberta | Publication | 2021-06-01 | |
Disaggregating Solar Generation Using Smart Meter Data and Proxy Measurements from Neighbouring SitesC-IoT2 University of Alberta | Publication | 2021-06-01 | |
ObscureNet: Learning Attribute-invariant Latent Representation for Anonymizing Sensor DataC-IoT2 University of Alberta | Publication | 2021-05-01 | |
Advances in Distribution System Monitoring University of Alberta | Publication | 2020-01-01 | |
COBS: COmprehensive Building SimulatorC-IoT2 University of Alberta | Publication | 2020-11-01 | |
Solar Disaggregation: State of the Art and Open Challenges University of Alberta | Publication | 2020-11-01 | |
Large-scale Data-driven Segmentation of Banking Customers University of Alberta | Publication | 2020-12-01 | Md Monir Hossain, Mark Sebestyen, Dhruv Mayank, Omid Ardakanian, Hamzeh Khazaei |
A Holistic Machine Learning-based Autoscaling Approach for Microservice Applications University of Alberta | Publication | 2021-01-01 | |
Adaptive Congestion Control for Electric Vehicle Charging in the Smart Grid University of Alberta | Publication | 2021-05-01 | |
Identifying grey-box thermal models with Bayesian neural networks University of Alberta | Publication | 2021-05-01 | |
Flexible, decentralised access control for smart buildings with smart contractsC-IoT2 University of Alberta | Publication | 2021-07-01 | |
Migrating from Monolithic to Serverless: A FinTech Case Study University of Alberta | Publication | 2020-04-01 | Alireza Goli, Omid Hajihassani, Hamzeh Khazaei, Omid Ardakanian, Moe Rashidi, Tyler Dauphinee |
Latent Representation Learning and Manipulation for Privacy-Preserving Sensor Data Analytics University of Alberta | Publication | 2020-04-01 | |
Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation ApproachC-IoT2 University of Alberta | Publication | 2022-02-01 | |
Addressing Data Inadequacy Challenges in Personal Comfort Models by Combining Pretrained Comfort ModelsC-IoT2, P-Apps27 University of Alberta | Publication | 2022-06-01 | |