I will be attending IEEE ISGT 2020 with two accepted papers. This influential conference with be held in Washington D.C. February 17-20, 2020. Here are details of the two papers:
Increasing the Accuracy and Speed of Universal Non-Intrusive Load Monitoring (UNILM) Using a Novel Real-Time Steady-State Block Filter
Autors: Richard Jones, Alejandro Rodriguez-Silva, Stephen Makonin
Abstract: Non-intrusive load monitoring (NILM) is a research field focused on developing algorithms that can accurately track constituent electrical loads in a system using only the aggregate signal alone (i.e., smart meter). It is widely understood that having a clean signal free of noise and transient behaviour, whether for event-based or state-based methods, can lead to more accurate solutions that will eventually solve the NILM problem. We propose a fast and highly reliable method for producing a block-like representation of signals. Using the same data and disaggregation technique, we compare our algorithm with a recent similar effort and show significant improvements in accuracy (98% vs. 94% tracked energy over three appliances) and run-time (143ms vs. 891s). Application of our method to raw mains power data shows it can generalize to more complex cases.
Keywords: unsupervised learning, disaggregation, non- intrusive load monitoring, NILM, universal NILM, UNILM, adaptive filter, smart meter, smart grid
Towards Comparability in Non-Intrusive Load Monitoring: On Data and Performance Evaluation
Autors: Christoph Klemenjak, Stephen Makonin, Wilfried Elmenreich
Abstract: Non-Intrusive Load Monitoring (NILM) comprises of a set of techniques that provide insights into the energy consumption of households and industrial facilities. Latest contributions show significant improvements in terms of accuracy and generalisation abilities. Despite all progress made concerning disaggregation techniques, performance evaluation and comparability remains an open research question. The lack of standardisation and consensus on evaluation procedures makes reproducibility and comparability extremely difficult. In this paper, we draw attention to comparability in NILM with a focus on highlighting the considerable differences amongst common energy datasets used to test the performance of algorithms. We divide discussion on comparability into data aspects, performance metrics, and give a close view on evaluation processes. Detailed information on pre-processing as well as data cleaning methods, the importance of unified performance reporting, and the need for complexity measures in load disaggregation are found to be the most urgent issues in NILM-related research. In addition, our evaluation suggests that datasets should be chosen carefully. We conclude by formulating suggestions for future work to enhance comparability.
Keywords: NILM, load disaggregation, comparability, performance evaluation, data engineering
Hope to see you at IEEE ISGT 2020!