Ioannis C. Konstantakopoulos

PresenceSense: zero-training algorithm for individual presence detection based on power monitoring

Non-intrusive presence detection of individuals in commercial buildings is much easier to implement than intrusive methods such as passive infrared, acoustic sensors, and camera. Individual power consumption, while providing useful feedback and motivation for energy saving, can be used as a valuable source for presence detection. We conduct pilot experiments in an office setting to collect individual presence data by ultrasonic sensors, acceleration sensors, and WiFi access points, in addition to the individual power monitoring data. PresenceSense (PS), a semi-supervised learning algorithm based on power measurement that trains itself with only unlabeled data, is proposed, analyzed and evaluated in the study. Without any labeling efforts, which are usually tedious and time consuming, PresenceSense outperforms popular models whose parameters are optimized over a large training set. The results are interpreted and potential applications of PresenceSense on other data sources are discussed. The significance of this study attaches to space security, occupancy behavior modeling, and energy saving of plug loads.

Model-Based Fault Detection and Identification for Switching Power Converters

We present the analysis, design, and experimental validation of a model-based fault detection and identification (FDI) method for switching power converters using a model-based state estimator approach. The proposed FDI approach is general in that it can be used to detect and identify arbitrary faults in components and sensors in a broad class of switching power converters. The FDI approach is experimentally demonstrated on a nanogrid prototype with a 380-V dc distribution bus. The nanogrid consists of four different switching power converters, including a buck converter, an interleaved boost converter, a single-phase rectifier, and a three-phase inverter. We construct a library of fault signatures for possible component and sensor faults in all four converters. The FDI algorithm successfully achieves fault detection in under 400

Abnormal event detection with high resolution micro-PMU data

\mu

Data-driven event detection with partial knowledge: A Hidden Structure Semi-Supervised learning method

s and fault identification in under 10 ms for faults in each converter. The proposed FDI approach enables a flexible and scalable solution for improving fault tolerance and awareness in power electronics systems.

Social game for building energy efficiency: Incentive design

Power system has been incorporating increasing amount of unconventional generations and loads such as renewable resources, electric vehicles, and controllable loads. The induced short term and stochastic power flow requires high resolution monitoring technology and agile decision support techniques for system diagnosis and control. In this paper, we discuss the application of micro-phasor measurement unit (μPMU) for power distribution network monitoring, and study learning based data-driven methods for abnormal event detection. We first resolve the challenging problem of information representation for the multiple streams of high resolution μPMU data, by proposing a pooling-picking scheme. With that, a kernel Principle Component Analysis (kPCA) is adopted to build statistical models for nominal state and detect possible anomalies. To distinguish event types, we propose a novel discriminative method that only requires partial expert knowledge for training. Finally, our methods are tested on an actual distribution network with μPMUs, and the results justifies the effectiveness of the data driven event detection framework, as well as its potentials to serve as one of the core algorithms to ensure power system security and reliability.

Diagnosing wind turbine faults using machine learning techniques applied to operational data

Enabled by the advancement of data acquisition and data analysis technologies such as sensor networks and machine learning, recently data-driven event detection has shown its advantage in dealing with complex systems especially those with significant stochastic and dynamic behavior. However, existing methods usually adopt supervised learning framework and depend on explicit expert labeling in the learning phase, which is expensive even impractical in many situations. In this work, we propose a new data-driven event detection method, namely Hidden Structure Semi-Supervised Machine (HS3M), that only requires partial expert knowledge. The key idea is to combine unlabeled data and partly labeled data in a large margin learning objective to bridge the gap between supervised, semi-supervised learning and learning with hidden structures. Difficulties do arise as the incorporation of extra learning terms makes the problem non-convex. To optimize the learning objective we establish a novel global optimization algorithm, namely Parametric Dual Optimization Procedure (PDOP), by showing that the parametrized dual problem has local explicit solutions and the corresponding optimality is convex in hidden variables. The proposed approach is applied to power distribution network event detection, and the result justifies the effectiveness of both HS3M and the new global optimization algorithm.

Real-time model-based fault diagnosis for switching power converters

We present analysis and results of a social game encouraging energy efficient behavior in occupants by distributing points which determine the likelihood of winning in a lottery. We estimate occupants utilities and formulate the interaction between the building manager and the occupants as a reversed Stackelberg game in which there are multiple followers that play in a non-cooperative game. The estimated utilities are used for determining the occupant behavior in the non-cooperative game. Due to nonconvexities and complexity of the problem, in particular the size of the joint distribution across the states of the occupants, we solve the resulting the bilevel optimization problem using a particle swarm optimization method. Drawing from the distribution across player states, we compute the Nash equilibrium of the game using the resulting leader choice. We show that the behavior of the agents under the leader choice results in greater utility for the leader.

Smart building energy efficiency via social game: a robust utility learning framework for closing–the–loop

Unscheduled or reactive maintenance on wind turbines due to component failures incurs significant downtime and, in turn, loss of revenue. To this end, it is important to be able to perform maintenance before its needed. By continuously monitoring turbine health, it is possible to detect incipient faults and schedule maintenance as needed, negating the need for unnecessary periodic checks. To date, a strong effort has been applied to developing Condition monitoring systems (CMSs) which rely on retrofitting expensive vibration or oil analysis sensors to the turbine. Instead, by performing complex analysis of existing data from the turbines Supervisory Control and Data Acquisition (SCADA) system, valuable insights into turbine performance can be obtained at a much lower cost. In this paper, data is obtained from the SCADA system of a turbine in the South-East of Ireland. Fault and alarm data is filtered and analysed in conjunction with the power curve to identify periods of nominal and fault operation. Classification techniques are then applied to recognise fault and fault-free operation by taking into account other SCADA data such as temperature, pitch and rotor data. This is then extended to allow prediction and diagnosis in advance of specific faults. Results are provided which show success in predicting some types of faults.

REST: a reliable estimation of stopping time algorithm for social game experiments

We present the analysis, design, and experimental implementation of a fault diagnosis method for switching power converters using a model-based estimator approach. The fault diagnosis method enables efficient detection and identification of component and sensor faults, and is implemented on the same computation platform as the control system. The model-based estimator operates in parallel with the switching power converter, and generates an error residual vector that can be used to detect and identify particular component or sensor faults. This paper presents an experimental demonstration for a 1.2 kW rack-level uninterruptable power supply (UPS) dc-dc converter for data center applications. Simulation and experimental results demonstrate fault detection and identification for various component and sensor faults in the converter. Moreover, we show that the proposed fault diagnosis design and analysis methods are applicable to a broad class of converter topologies and fault types.

A Robust Utility Learning Framework via Inverse Optimization

Given a non-cooperative, continuous game, we describe a framework for parametric utility learning. Using heteroskedasticity inference, we adapt a Constrained Feasible Generalized Least Squares (cFGLS) utility learning method in which estimator variance is reduced, unbiased, and consistent. We extend our utility learning method using bootstrapping and bagging. We show the performance of the proposed method using data from a social game experiment designed to encourage energy efficient behavior amongst building occupants. Using occupant voting data we simulate the game defined by the estimated utility functions and show that the performance of our robust utility learning method and quantify its improvement over classical methods such as Ordinary Least Squares (OLS).