Incorporating Appliance Usage Patterns for Non-Intrusive Load Monitoring and Load Forecasting

Abstract

This paper proposes a novel Non-Intrusive Load Monitoring (NILM) method which incorporates appliance usage patterns (AUPs) to improve performance of active load identification and forecasting. In the first stage, the AUPs of a given residence were learnt using a spectral decomposition based standard NILM algorithm. Then, learnt AUPs were utilized to bias the priori probabilities of the appliances through a specifically constructed fuzzy system. The AUPs contain likelihood measures for each appliance to be active at the present instant based on the recent activity/inactivity of appliances and the time of day. Hence, the priori probabilities determined through the AUPs increase the active load identification accuracy of the NILM algorithm. The proposed method was successfully tested for two standard databases containing real household measurements in USA and Germany. The proposed method demonstrates an improvement in active load estimation when applied to the aforementioned databases as the proposed method augments the smart meter readings with the behavioral trends obtained from AUPs. Furthermore, a residential power consumption forecasting mechanism, which can predict the total active power demand of an aggregated set of houses, five minutes ahead of real time, was successfully formulated and implemented utilizing the proposed AUP based technique.

Robust energy disaggregation using appliance-specific temporal contextual information

“…To further compare the results with the NILM methods proposed in the literature, the very recent work of [66] was used, which includes a summary of NILM performances for the REDD database for different setups. Approaches using the most popular experimental The best performing length of the temporal contextual window w for each of the evaluated datasets is indicated in italics set-up using houses 1, 2, 3, 4, and 6 with all devices and measuring performance using the E ACC metric were considered.…”

“…Approaches using the most popular experimental The best performing length of the temporal contextual window w for each of the evaluated datasets is indicated in italics set-up using houses 1, 2, 3, 4, and 6 with all devices and measuring performance using the E ACC metric were considered. Moreover, the results from [66] were extended by including recently published results [67,68] on the same experimental set-up. It is worth mentioning that although the same data and the same accuracy metric was used, direct comparison is not assured as data splits or preprocessing might vary between the compared approaches (such information is not provided in most papers found in the bibliography).…”

NILM Techniques for Intelligent Home Energy Management and Ambient Assisted Living: A Review

“…This is the case, for instance, with [129], where, using only a single active power sample acquired at the general entry point with a rate of 1 Hz, it is feasible to distinguish turned ON appliances, their operating modes, as well as power consumption, together with the amount of solar power. In a more recent work [130], the authors extended their previous solution and were able to properly forecast the active power demand of a set of five households.…”

“…Physiological signals related to direct monitoring methods are often blood oxygen saturation, heart rate and breathing [130]. The acquisition of these signals is normally very accurate, but difficult to scale since the corresponding transducers required to be attached to the body.…”

Optimal Decomposition and Reconstruction of Discrete Wavelet Transformation for Short-Term Load Forecasting

“…The user behavior model is built to estimate the exact load signals by considering various inputs, such as user daily schedules, as investigated by Stephen et al [4] and Sajjad et al [5], while Perfumo et al [6] used specific temperature formulation. Another way to investigate user behavior is by using non-intrusive load monitoring to know status of each set of appliances as proposed by Welikala et al [7]. However, information to build user behavior is scarcer in the wide area data set and driven by the seasonal effect of the time series, a fact that makes this approach less attractive, as applied in the work of Kong et al [8], Xie et al [9], and Erdinc et al [10].…”