As the number of smart meters increases, compression of metering data becomes essential for data transmission, storing and processing perspectives. Specifically, feature extraction can be used for the compression of metering data and further be utilized for smart grid applications such as customer clustering. So far, there are many studies for compression and clustering based on daily load profiles. However, in order to account for long-term characteristics of electricity consumption, utilizing yearly load profiles (YLPs) is vital for customer load clustering and analysis. In this paper, we propose a deep learning based YLP compression that jointly captures daily and seasonal variations. By leveraging convolutional autoencoder (CAE), YLPs in 8,640-dimensional space are compressed to 100-dimensional vectors. We apply the proposed CAE framework to YLPs of 1,405 residential customers and verify that the proposed CAE outperforms other dimensionality reduction methods in terms of reconstruction errors, e.g., by 19-40%, or the compression ratio is increased by 130% or higher than other methods for the same reconstruction error. In addition, clustering analysis is performed on the encoded YLPs. Our results confirm that year-round characteristics are well captured during the clustering process and also clearly visualized with load images.
17 July 2019 in Proceedings of the AAAI Conference on Artificial Intelligence
Non-intrusive load monitoring (NILM), also known as energy disaggregation, is a blind source separation problem where a household’s aggregate electricity consumption is broken down into electricity usages of individual appliances. In this way, the cost and trouble of installing many measurement devices over numerous household appliances can be avoided, and only one device needs to be installed. The problem has been well-known since Hart’s seminal paper in 1992, and recently significant performance improvements have been achieved by adopting deep networks. In this work, we focus on the idea that appliances have on/off states, and develop a deep network for further performance improvements. Specifically, we propose a subtask gated network that combines the main regression network with an on/off classification subtask network. Unlike typical multitask learning algorithms where multiple tasks simply share the network parameters to take advantage of the relevance among tasks, the subtask gated network multiply the main network’s regression output with the subtask’s classification probability. When standby-power is additionally learned, the proposed solution surpasses the state-of-the-art performance for most of the benchmark cases. The subtask gated network can be very effective for any problem that inherently has on/off states.
AMI has been gradually replacing conventional meters because newer models can acquire more informative energy consumption data. The additional information has enabled significant advances in many fields, including energy disaggregation, energy consumption pattern analysis and prediction, demand response, and user segmentation. However, the quality of AMI data varies significantly across publicly available datasets, and low sampling rates and numbers of houses monitored seriously limit practical analyses. To address these challenges, we herein present the ENERTALK dataset, which contains both aggregate and per-appliance measurements sampled at 15 Hz from 22 houses. Among the publicly available datasets with both aggregate and per-appliance measurements, 15 Hz was the highest sampling rate. The number of houses (22) was the second-largest where the largest one had a sampling rate of 1 Hz. The ENERTALK dataset is also the first Korean open dataset on residential electricity consumption.
Energy disaggregation, or nonintrusive load monitoring (NILM), is a technology for separating a household’s aggregate electricity consumption information. Although this technology was developed in 1992, its practical usage and mass deployment have been rather limited, possibly because the commonly used datasets are not adequate for NILM research. In this study, we report the findings from a newly collected dataset that contains 10 Hz sampling data for 58 houses. The dataset not only contains the aggregate measurements, but also individual appliance measurements for three types of appliances. By applying three classification algorithms (vanilla DNN (Deep Neural Network), ML (Machine Learning) with feature engineering, and CNN (Convolutional Neural Network) with hyper-parameter tuning) and a recent regression algorithm (Subtask Gated Network) to the new dataset, we show that NILM performance can be significantly limited when the data sampling rate is too low or when the number of distinct houses in the dataset is too small. The well-known NILM datasets that are popular in the research community do not meet these requirements. Our results indicate that higher quality datasets should be used to expedite the progress of NILM research.
Solar power is an important renewable energy resource that plays a pivotal role in replacing fossil fuel generators and lowering carbon emissions. Since sunlight, which is highly dependent on meteorological factors, is highly volatile, the difficulty in collecting real-time data from renewable energy power plants poses a major threat to maintaining the stability of the entire power system in the target area. A high-performance wireless metering modem is required to monitor the renewable energy generation power of the entire target area in real-time. However, installing such devices on all sites is expensive, so we propose a system that uses deep learning to estimate the generation power of a target site based on the power generations of some sample sites. We use clustering and distance-based sampling to extract a sample site corresponding to each target site and use the recurrent neural network (RNN)-based attention techniques to estimate the generation of target sites from the sample sites. Our experiments show that the proposed RNN-based attention models significantly improve estimation accuracy compared to the baseline model or other deep learning models, irrespective of the number or location of sample sites.
In this paper, we provide findings from an energy saving experiment in a university building, where an IoT platform with 1 Hz sampling sensors was deployed to collect electric power consumption data. The experiment was a reward setup with daily feedback delivered by an energy delegate for one week, and energy saving of 25.4% was achieved during the experiment. Post-experiment sustainability, defined as 10% or more of energy saving, was also accomplished for 44 days without any further intervention efforts. The saving was possible mainly because of the data-driven intervention designs with high-resolution data in terms of sampling frequency and number of sensors, and the high-resolution data turned out to be pivotal for an effective waste behavior investigation. While the quantitative result was encouraging, we also noticed many uncontrollable factors, such as exams, papers due, office allocation shuffling, graduation, and new-comers, that affected the result in the campus environment. To confirm that the quantitative result was due to behavior changes, rather than uncontrollable factors, we developed several data-driven behavior detection measures. With these measures, it was possible to analyze behavioral changes, as opposed to simply analyzing quantitative fluctuations. Overall, we conclude that the space-time resolution of data can be crucial for energy saving, and potentially for many other data-driven energy applications.