Feature Extraction from Building Submetering Networks Using Deep Learning

Abstract

<jats:p>The understanding of the nature and structure of energy use in large buildings is vital for defining novel energy and climate change strategies. The advances on metering technology and low-cost devices make it possible to form a submetering network, which measures the main supply and other intermediate points providing information of the behavior of different areas. However, an analysis by means of classical techniques can lead to wrong conclusions if the load is not balanced. This paper proposes the use of a deep convolutional autoencoder to reconstruct the whole consumption measured by the submeters using the learnt features in order to analyze the behavior of different building areas. The display of weights and information of the latent space provided by the autoencoder allows us to obtain precise details of the influence of each area in the whole building consumption and its dependence on external factors such as temperature. A submetering network is deployed in the León University Hospital building in order to test the proposed methodology. The results show different correlations between environmental variables and building areas and indicate that areas can be grouped depending on their function in the building performance. Furthermore, this approach is able to provide discernible results in the presence of large differences with respect to the consumption ranges of the different areas, unlike conventional approaches where the influence of smaller areas is usually hidden.</jats:p>

Scattering Transform for Classification in Non-Intrusive Load Monitoring

“…The wavelet transform has the advantage of time-warping stability, but the data used in [12] were submetered, and not naturally aggregated. The same limitation is found in [12,36]. Particularly in [36], the authors employed a deep convolutional autoencoder to extract features from individual hospital loads.…”

“…The same limitation is found in [12,36]. Particularly in [36], the authors employed a deep convolutional autoencoder to extract features from individual hospital loads. Nevertheless, there is no disaggregation since the CNN input is obtained from a submetering network.…”

Gap imputation in related multivariate time series through recurrent neural network-based denoising autoencoder

“…Another cooling load prediction model was developed for commercial buildings, using a thermal network model and a submetering system [28]. A study of relevant features based on deep learning was presented in [29] using data from a submetering system in a hospital facility. Furthermore, energy disaggregation techniques, such as non-intrusive load monitoring (NILM), were applied [30,31] to recognize individual measurements from aggregated data [32][33][34].…”

Recent advances in smart grid architecture and grid-electric vehicle-charging station interaction

“…Smart metering technology comprises the following components:  Smart metering meters: Smart meters are the core of smart metering technology. As they can measure energy consumption in real-time and transmit data directly back to the user via communication networks, they will completely replace traditional electricity meters, water meters, etc., in the future [6].  Data communication network: innovative metering technology requires a reliable data communication network to transmit the data collected from smart meters.…”