Smart meter roll-outs provide easy access to granular meter measurements, enabling advanced energy services, ranging from demand response measures, tailored energy feedback and smart home/building automation. To design such services, train and validate models, access to data that resembles what is expected of smart meters, collected in a real-world setting, is necessary. The REFIT electrical load measurements dataset described in this paper includes whole house aggregate loads and nine individual appliance measurements at 8-second intervals per house, collected continuously over a period of two years from 20 houses. During monitoring, the occupants were conducting their usual routines. At the time of publishing, the dataset has the largest number of houses monitored in the United Kingdom at less than 1-minute intervals over a period greater than one year. The dataset comprises 1,194,958,790 readings, that represent over 250,000 monitored appliance uses. The data is accessible in an easy-to-use comma-separated format, is time-stamped and cleaned to remove invalid measurements, correctly label appliance data and fill in small gaps of missing data.

With the large-scale roll-out of smart metering worldwide, there is a growing need to account for the individual contribution of appliances to the load demand. In this paper, we design a graph signal processing (GSP)-based approach for non-intrusive appliance load monitoring (NILM), i.e., disaggregation of total energy consumption down to individual appliances used. Leveraging piecewise smoothness of the power load signal, two GSP-based NILM approaches are proposed. The first approach, based on total graph variation minimization, searches for a smooth graph signal under known label constraints. The second approach uses the total graph variation minimizer as a starting point for further refinement via simulated annealing. The proposed GSP-based NILM approach aims to address the large training overhead and associated complexity of conventional graph-based methods through a novel event-based graph approach. Simulation results using two datasets of real house measurements demonstrate the competitive performance of the GSP-based approaches with respect to traditionally used hidden Markov model-based and decision tree-based approaches.

With ongoing large-scale smart energy metering deployments worldwide, disaggregation of a household's total energy consumption down to individual appliances using analytical tools, also known as non-intrusive appliance load monitoring (NALM), has generated increased research interest lately. NALM can deepen energy feedback, support appliance retrofit advice, and support home automation. However, despite the fact that NALM was proposed over 30 years ago, there are still many open challenges with respect to its practicality and effectiveness at low sampling rates. Indeed, the majority of NALM approaches, supervised or unsupervised, require training to build appliance models, and are sensitive to appliance changes in the house, thus requiring regular re-training. In this paper, we tackle this challenge by proposing an NALM approach that does not require any training. The main idea is to build upon the emerging field of graph signal processing to perform adaptive thresholding, signal clustering, and pattern matching. We determine the performance limits of our approach and demonstrate its usefulness in practice. Using two open access datasets-the US REDD data set with active power measurements downsampled to 1 min resolution and the UK REFIT data set with 8-s resolution, we demonstrate the effectiveness of the proposed method for typical smart meter sampling rate, with the state-of-the-art supervised and unsupervised NALM approaches as benchmarks.

This paper proposes a direct model for conditional probability density forecasting of residential loads, based on a deep mixture network. Probabilistic residential load forecasting can provide comprehensive information about future uncertainties in demand. An end-to-end composite model comprising convolution neural networks (CNNs) and gated recurrent unit (GRU) is designed for probabilistic residential load forecasting. Then, the designed deep model is merged into a mixture density network (MDN) to directly predict probability density functions (PDFs). In addition, several techniques, including adversarial training, are presented to formulate a new loss function in the direct probabilistic residential load forecasting (PRLF) model. Several state-of-the-art deep and shallow forecasting models are also presented in order to compare the results. Furthermore, the effectiveness of the proposed deep mixture model in characterizing predicted PDFs is demonstrated through comparison with kernel density estimation, Monte Carlo dropout, a combined probabilistic load forecasting method and the proposed MDN without adversarial training.

Fountain codes were introduced as an efficient and universal forward error correction (FEC) solution for data multicast over lossy packet networks. They have recently been proposed for large scale multimedia content delivery in practical multimedia distribution systems. However, standard fountain codes, such as LT or Raptor codes, are not designed to meet unequal error protection (UEP) requirements typical in real-time scalable video multicast applications. In this paper, we propose recently introduced UEP expanding window fountain (EWF) codes as a flexible and efficient solution for real-time scalable video multicast. We demonstrate that the design flexibility and UEP performance make EWF codes ideally suited for this scenario, i.e., EWF codes offer a number of design parameters to be ldquotunedrdquo at the server side to meet the different reception criteria of heterogeneous receivers. The performance analysis using both analytical results and simulation experiments of H.264 scalable video coding (SVC) multicast to heterogeneous receiver classes confirms the flexibility and efficiency of the proposed EWF-based FEC solution.