Search

Evaluations of nonintrusive load monitoring (NILM) algorithms and technologies have mostly occurred in constrained, artificial environments. However, few field evaluations of NILM products have taken place in actual buildings under normal operating conditions. This paper describes a field evaluation of a state-of-the-art NILM product, tested in eight homes. The match rate metric—a technique recommended by a technical advisory group—was used to measure the NILM's success in identifying specific loads and the accuracy of the energy consumption estimates. A performance assessment protocol was also developed to address common issues with NILM mislabeling and ground-truth comparisons that have not been sufficiently addressed in past evaluations. The NILM product's estimates were compared to the submetered consumption of eight major appliances. Overall, the product had good performance in disaggregating the energy consumption of the electric water heaters, which included both electric resistance and heat-pump water heaters, but only a fair accuracy with refrigerators, dryers, and air conditioners. The performance was poor for cooking equipment, furnace fans, clothes washers, and dishwashers. Moreover, the product was often unable to detect major loads in homes. Typically, two or more appliances were not detected in a home. At least two dryers, furnace fans, and air conditioners went undetected across the eight homes. On the other hand, the dishwasher was detected in all homes where available or monitored. The key findings were qualitatively compared to those of past field evaluations. Potential areas for improvement in NILM product performance were determined along with areas where complementary technologies may be able to aid in load-disaggregation applications. [ABSTRACT FROM AUTHOR]

Identifying flexible loads, such as a heat pump, has an essential role in a home energy management system. In this study, an adaptive ensemble filtering framework integrated with long short-term memory (LSTM) is proposed for identifying flexible loads. The proposed framework, called AEFLSTM, takes advantage of filtering techniques and the representational power of LSTM for load disaggregation by filtering noise from the total power and learning the long-term dependencies of flexible loads. Furthermore, the proposed framework is adaptive and searches ensemble filtering techniques, including discrete wavelet transform, low-pass filter, and seasonality decomposition, to find the best filtering method for disaggregating different flexible loads (e.g., heat pumps). Experimental results are presented for estimating the electricity consumption of a heat pump, a refrigerator, and a dishwasher from the total power of a residential house in British Columbia (a publicly available use case). The results show that AEFLSTM can reduce the loss error (mean absolute error) by 57.4%, 44%, and 55.5% for estimating the power consumption of the heat pump, refrigerator, and dishwasher, respectively, compared to the stand-alone LSTM model. The proposed approach is used for another dataset containing measurements of an electric vehicle to further support the validity of the method. AEFLSTM is able to improve the result for disaggregating an electric vehicle by 22.5%. [ABSTRACT FROM AUTHOR]

The demand for electricity has been rising significantly over the past years and it is expected to rise further in the coming years due to economic and societal development. Smart grid technology is being developed in order to meet the rising electricity requirement. In order for the smart grid to perform its full functions, the Energy Management Systems (EMSs), especially Home Energy Management Systems (HEMS) are essential. It is necessary to understand the energy demand of the loads and the energy supply either from the national grid or from renewable energy technologies. To facilitate the Demand Side Management (DSM), Heat Pumps (HP) and air conditioning systems are often utilised for heating and cooling in residential houses due to their high-efficiency power output and low CO2 emissions. This paper presents a program for a HEMS using a Particle Swarm Optimisation (PSO) algorithm. A HP is used as the load and the aim of the optimisation program is to minimise the operational cost, i.e., the cost of electricity, while maintaining end-user comfort levels. This paper also details an indoor thermal model for temperature update in the heat pump control program. Real measured data from the UK Government's Renewable Heat Premium Payment (RHPP) scheme was utilised to generate characteristic curves and equations that can represent the data. This paper compares different PSO variants with standard PSO and the unscheduled case calculated from the data for five winter days in 2019. Among all chosen algorithms, the Crossover Subswarm PSO (CSPSO) achieved an average saving of 25.61% compared with the cost calculated from the measured data with a short search time of 1576 ms for each subswarm. It is clear from this work that there is significant scope to reduce the cost of operating a HP while maintaining end user comfort levels. [ABSTRACT FROM AUTHOR]

The utilization of groundwater is becoming increasingly popular for heating and cooling buildings, as well as to regulate the temperature needs of industrial processes. Groundwater has excellent energy potential from various factors, of which environmental acceptability stands out, as groundwater is considered a source of renewable energy. Due to the water table depth below the surface, atmospheric conditions have a negligible effect on the temperature of groundwater, resulting only in minor annual temperature variations, thus also making groundwater a source of reliable renewable energy. This paper presents some aspects of the groundwater heat pump (GWHP) system's design and addresses a particular problem on the influence of recharge temperature field as well as local utility lines on the pumping well water temperature. An example is given of a system designed for a production hall in the northern part of Croatia. Geological and hydrogeological conditions at the site are highly favourable regarding the groundwater temperature and aquifer parameters. For the needs of this research, precise electronic sensors with data loggers were installed inside the wells. Probe type GSR 120 NT manufactured by Eltratec, Slovenia, is capable of monitoring level, temperature, and electrical conductivity, including telemetric data transfer to the remote server. Mapping the obtained data revealed significant temperature breakthroughs from the recharge wells, as well as local temperature field deviation near the sanitary and precipitation drainage collectors. Utility installation seepage influence was differentiated by the increase in groundwater electrical conductivity measured at the pumping wells. Results show that not only distance between the wells, as the main parameter that affects the system, but also industrial utility lines can have an influence on thermal field breakthrough. [ABSTRACT FROM AUTHOR]

With the large-scale deployment of smart meters worldwide, research in non-intrusive load monitoring (NILM) has seen a significant rise due to its dual use of real-time monitoring of end-user appliances and user-centric feedback of power consumption usage. NILM is a technique for estimating the state and the power consumption of an individual appliance in a consumer's premise using a single point of measurement device such as a smart meter. Although there are several existing NILM techniques, there is no meaningful and accurate metric to evaluate these NILM techniques for multi-state devices such as the fridge, heat pump, etc. In this paper, we demonstrate the inadequacy of the existing metrics and propose a new metric that combines both event classification and energy estimation of an operational state to give a more realistic and accurate evaluation of the performance of the existing NILM techniques. In particular, we use unsupervised clustering techniques to identify the operational states of the device from a labeled dataset to compute a penalty threshold for predictions that are too far away from the ground truth. Our work includes experimental evaluation of the state-of-the-art NILM techniques on widely used datasets of power consumption data measured in a real-world environment. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology for dealing with an issue of crucial practical importance in real engineering systems such as fault detection and recovery of a sensor. The main goal is to define a strategy to identify a malfunctioning sensor and to establish the correct measurement value in those cases. As study case, we use the data collected from a geothermal heat exchanger installed as part of the heat pump installation in a bioclimatic house. The sensor behaviour is modeled by using six different machine learning techniques: Random decision forests, gradient boosting, extremely randomized trees, adaptive boosting, k-nearest neighbors, and shallow neural networks. The achieved results suggest that this methodology is a very satisfactory solution for this kind of systems. [ABSTRACT FROM AUTHOR]