Abstract
The central problems of some of the existing Non-Intrusive Load Monitoring (NILM) algorithms are indicated as: (1) higher required electrical device identification accuracy; (2) the fact that they enable training over a larger device count; and (3) their ability to be trained faster, limiting them from usage in industrial premises and external grids due to their sensitivity to various device types found in residential premises. The algorithm accuracy is higher compared to previous work and is capable of training over at least thirteen electrical devices collaboratively, a number that could be much higher if such a dataset is generated. The algorithm trains the data around 1.8×108 faster due to a higher sampling rate. These improvements potentially enable the algorithm to be suitable for future “grids and industrial premises load identification” systems. The algorithm builds on new principles: an electro-spectral features preprocessor, a faster waveform sampling sensor, a shorter required duration for the recorded data set, and the use of current waveforms vs. energy load profile, as was the case in previous NILM algorithms. Since the algorithm is intended for operation in any industrial premises or grid location, fast training is required. Known classification algorithms are comparatively trained using the proposed preprocessor over residential datasets, and in addition, the algorithm is compared to five known low-sampling NILM rate algorithms. The proposed spectral algorithm achieved 98% accuracy in terms of device identification over two international datasets, which is higher than the usual success of NILM algorithms.
Highlights
Non-intrusive load monitoring (NILM) is a highly investigated discipline and application used by many researchers with various AI algorithms associated with various issues
The following were listed as objects: (1) improve device identification accuracy; (2) Enhance training due to the high sampling rate; (3) create a situation where less computational effort is need in order for the algorithm to act as a gate and an enabler to industrial premises deployment; (4) report on the training process when using larger device counts than previous works; and (5) conduct a comparative study investigating several classifiers in comparison to the proposed preprocessor along with the effects and comparing these effects to previous works
The location of entire code using for the training dataset is indicated in the Introduction, and the code is executable there
Summary
Non-intrusive load monitoring (NILM) is a highly investigated discipline and application used by many researchers with various AI algorithms associated with various issues When it is based on the electricity load profile, periodic energy recording, which occurs quarter-hourly up to one-hourly, it is called low-sampling rate NILM. A recent work describing this is by Renaux et al [14], who proposed an LIT dataset This is important because (1) it states the methodology required for low-sampling rate algorithms as a dataset, and (2) because it mentions the insufficiency and inaccuracy of algorithms after they have been trained with the dataset while operating at various premises. Two highly quoted datasets are REDD [27] from Stanford and REDD [28] from
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
