Dominik Egarter

PALDi: Online Load Disaggregation via Particle Filtering

Smart metering and fine-grained energy data are one of the major enablers for future smart grid and improved energy efficiency in smart homes. Using the information provided by smart meter power draw, valuable information can be extracted as disaggregated appliance power draws by non-intrusive load monitoring (NILM). NILM allows to identify appliances according to their power characteristics in the total power consumption of a household, measured by one sensor, the smart meter. In this paper, we present an NILM approach, where the appliance states are estimated by particle filtering (PF). PF is used for nonlinear and non-Gaussian disturbed problems and is suitable to estimate the appliance state. ON/OFF appliances, multistate appliances, or combinations of them are modeled by hidden Markov models, and their combinations result in a factorial hidden Markov model modeling the household power demand. We evaluate the PF-based NILM approach on synthetic and on real data from a well-known dataset to show that our approach achieves an accuracy of 90% on real household power draws.

GREEND: An energy consumption dataset of households in Italy and Austria

Home energy management systems can be used to monitor and optimize consumption and local production from renewable energy. To assess solutions before their deployment, researchers and designers of those systems demand for energy consumption datasets. In this paper, we present the GREEND dataset, containing detailed power usage information obtained through a measurement campaign in households in Austria and Italy. We provide a description of consumption scenarios and discuss design choices for the sensing infrastructure. Finally, we benchmark the dataset with state-of-the-art techniques in load disaggregation, occupancy detection and appliance usage mining.

Evolving non-intrusive load monitoring

Non-intrusive load monitoring (NILM) identifies used appliances in a total power load according to their individual load characteristics. In this paper we propose an evolutionary optimization algorithm to identify appliances, which are modeled as on/off appliances. We evaluate our proposed evolutionary optimization by simulation with Matlab, where we use a random total load and randomly generated power profiles to make a statement of the applicability of the evolutionary algorithm as optimization technique for NILM. Our results shows that the evolutionary approach is feasible to be used in NILM systems and can reach satisfying detection probabilities.

Autonomous load disaggregation approach based on active power measurements

With the help of smart metering valuable information of the appliance usage can be retrieved. In detail, nonintrusive load monitoring (NILM), also called load disaggregation, tries to identify appliances in the power draw of an household. In this paper an unsupervised load disaggregation approach is proposed that works without a priori knowledge about appliances. The proposed algorithm works autonomously in real time. The number of used appliances and the corresponding appliance models are learned in operation and are progressively updated. The proposed algorithm is considering each useful and suitable detected power state. The algorithm tries to detect power states corresponding to on/off appliances as well as to multi-state appliances based on active power measurements in 1s resolution. We evaluated the novel introduced load disaggregation approach on real world data by testing the possibility to disaggregate energy demand on appliance level.

Integration of legacy appliances into home energy management systems

The progressive installation of renewable energy sources requires the coordination of energy consuming devices. At consumer level, this coordination can be done by a home energy management system (HEMS). Interoperability issues need to be solved among smart appliances as well as between smart and non-smart, i.e., legacy devices. We expect current standardization efforts to soon provide technologies to design smart appliances in order to cope with the current interoperability issues. Nevertheless, common electrical devices affect energy consumption significantly and therefore deserve consideration within energy management applications. This paper discusses the integration of smart and legacy devices into a generic system architecture and, subsequently, elaborates the requirements and components which are necessary to realize such an architecture including an application of load detection for the identification of running loads and their integration into existing HEM systems. We assess the feasibility of such an approach with a case study based on a measurement campaign on real households. We show how the information of detected appliances can be extracted in order to create device profiles allowing for their integration and management within a HEMS.

Integrating households into the smart grid

The success of the Smart Grid depends on its ability to collect data from heterogeneous sources such as smart meters and smart appliances, as well as the utilization of this information to forecast energy demand and to provide value-added services to users. In our analysis, we discuss requirements for collecting and integrating household data within smart grid applications. We put forward a potential system architecture and report state-of-the-art technologies that can be deployed towards this vision.

Proficiency of Power Values for Load Disaggregation

Load disaggregation techniques infer the operation of different power-consuming devices from a single measurement point that records the total power drawn over time. Thus, a device consuming power at the moment can be understood as information encoded in the power draw. However, similar power draws or similar combinations of power draws limit the ability to detect the currently active device set. We present an information coding perspective of load disaggregation to enable a better understanding of this process and support its future improvement. In typical cases of quantity and types of devices and their respective power consumption, not all possible device configurations can be mapped to distinguishable power values. We introduce the term proficiency to describe the suitability of a device set for load disaggregation. We provide the notion and calculation of entropy of the initial device states, mutual information of power values, and the resulting uncertainty coefficient or proficiency. We show that the proficiency is highly dependent on the device running probability, especially for devices with multiple states of power consumption. The application of the concept is demonstrated by artificial data as well as with actual power consumption data from real-world power draw data sets.

Appliance State Estimation based on Particle Filtering

Non-Intrusive Load Monitoring is a single-point metering approach to identify and to monitor household appliances according their appliance power characteristics. In this paper, we propose an unsupervised classification approach for appliance state estimation of on/off-appliances modeled by a Hidden Markov Model (HMM). To estimate the states of appliances, we use the sequential Monte Carlo or particle filtering (PF) method. The proposed algorithm is tested with MATLAB simulations and is evaluated according to correctly or incorrectly detected on/off events.

Worried about privacy? Let your PV converter cover your electricity consumption fingerprints

Solar power has emerged as one of the three most widely installed renewable energy sources around the globe. Photovoltaic (PV) capacity in excess of 150 GW had been installed in 2013 already, and many more installations are connected to worldwide power grids every day; especially in the form of small-scale PV plants in domestic environments. However, in order to connect PV installations to the power grid, their dc output must be converted to the nominal mains voltage and frequency through the use of converters. In this paper, we propose a novel approach to influence the maximum power point tracking (MPPT) component of such a PV converter in order to enable two main privacy-preserving operations: Firstly, by deliberately reducing the output power through changing the converters operating point, appliance operations can be emulated in order to pretend user presence during periods of absence. Secondly, by running the converter below optimum output power, and feeding real-time data of an appliance consumption to the device, it is able to hide the appliances operation from the households aggregate consumption. We present simulations results that prove how our modified converter design can hide appliance load signatures as well as how it can be used to emulate appliance signatures to falsely indicate user presence.

European End-User’s Level of Energy Consumption and Attitude Toward Smart Homes: A Case Study of Residential Sectors in Austria and Italy

Abstract This article presents a quantitative assessment of the level of energy consumption of inhabitants located in Carinthia and Friuli-Venezia Giulia. In addition, an analysis for the current structural barriers for smart powered homes and smart energy management systems is conducted. A questionnaire consisting of 43 questions is used to address the aforementioned issues. In particular, a sample size of 385 respondents with a confidence of 95% and marginal error of 5% is found to be representative of the adopted area. Based on the results, we modeled the average energy consumption of a typical 110 m2 area household with 16.8 kWh/day, a 2.6 kW peak, and a load factor of 27%. Furthermore, an average of 46% of the respondents expressed the willingness to exploit tariff systems for operating their electrical appliances, and about two thirds of the respondents declared that they care about the energy efficiency at their households. However, low renewable energy utilization is observed due to some existing structural barriers. Therefore, an analysis and a discussion are carried out to investigate these barriers. Finally, some recommendations are provided according to the obtained results.